{
  "aboutHtml": "<h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p>",
  "aboutText": "### 작업을 위한 멀티모달 모델\n\nGLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.\n\n### 긴 컨텍스트의 아키텍처\n\n모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.\n\n시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.\n\n### 추론, 도구, 데이터\n\n추론은 항상 활성화됩니다. 깊이는 `low`, `high`, `max` 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.\n\n도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.\n\n반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.\n\n### 시각 지시에 따른 개발\n\n모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.\n\n### 문서와 전문 분석\n\n프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.\n\n재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.\n\n### 동영상, 3차원 장면, 인터페이스\n\n에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.\n\n3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.\n\n이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.",
  "editorialOverlay": {
    "copy_fields": {
      "practical_html": "<h3>실제 활용 과제</h3><p>영어 기술 예제</p><pre><code>Audit a report calculation\n\nReview these report rows supplied as text: revenue 12,000; cost of goods 7,000; delivery expense 800; reported gross profit 4,200. The report defines gross profit as revenue minus cost of goods, excluding delivery. Identify the formula mismatch, show the defined calculation and suggest a separate label for the delivery-adjusted figure.</code></pre><h4>예상 결과</h4><pre><code>A formula check, arithmetic using the given definition and a suggested label distinguishing the two measures.</code></pre><h4>결과 확인</h4><pre><code>Check that the report&#x27;s stated definition, rather than an invented accounting rule, determines the correction.</code></pre>"
    },
    "copy_sha256": "47c0119bf72db5623569a7f51bf77cd3322d3aa62d11d57d83d4802dba67a8cc",
    "copy_source": {
      "locale": "ko",
      "pack_sha256": "0f56d90ba41881e1134accf82e57338f246f8753ca4c0cee929aaffada5d10e7",
      "record_model_id": "z-ai/glm-5.3-flash",
      "source_facts_sha256": "85fa8e4e2b8fe74b0f77e1ed02a0b4e9f92beac44c27c967aabb7248ae2d7aad",
      "validation_sha256": "a2ac2f28056280fc0b2ea34a501bf156d5ce155406e57e708edf30bfdf6bfdc6"
    },
    "html_sha256": "3f1904d43bb4616c809a87eae80a4bf47d9633e1f8b6456e2e4c391c481b4aea",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "ko",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\" selected>glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-690-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-690-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-690-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-690-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-690-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-690-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-690-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-690-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-690-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-690-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-690-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-690-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5.3-flash&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-690-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-690-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5.3-flash&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image&quot;,&quot;source&quot;:{&quot;type&quot;:&quot;base64&quot;,&quot;media_type&quot;:mime,&quot;data&quot;:b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-690-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-690-tab-2\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-5.3-flash&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-690-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-690-tab-3\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-5.3-flash&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-690-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-690-tab-4\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-5.3-flash&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5.3-flash",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-5.3-flash",
      "ordinal": 0,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-5.3-flash\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-5.3-flash\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-5.3-flash',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\" selected>glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\">glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\">glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\">glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\">glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\">glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:input_image,image_url}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-691-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-691-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-691-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-691-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-691-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-691-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-691-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-691-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-691-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-691-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-691-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-691-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5.3-flash&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-691-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-691-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5.3-flash&quot;, &quot;input&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;input_text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;input&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;input_image&quot;,&quot;image_url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-691-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-691-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-5.3-flash&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-691-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-691-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-5.3-flash&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-691-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-691-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-5.3-flash&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5.3-flash",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-5.3-flash",
      "ordinal": 1,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-5.3-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-5.3-flash\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-5.3-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\" selected>glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image_url,image_url:{url,detail}}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-692-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-692-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-692-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-692-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-692-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-692-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-692-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-692-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-692-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-692-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-692-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-692-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5.3-flash&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-692-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-692-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5.3-flash&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image_url&quot;,&quot;image_url&quot;:{&quot;url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-692-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-692-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-5.3-flash&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-692-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-692-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-5.3-flash&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-692-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-692-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-5.3-flash&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5.3-flash",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-5.3-flash",
      "ordinal": 2,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-5.3-flash\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-5.3-flash\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\" selected>glm-5.3-flash</option><option value=\"Ultra|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option><option value=\"Ultra|chat|/v1/chat/completions|~z-ai%2Fglm-flash-latest\">~z-ai/glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-3\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 텍스트 대화</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>messages</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>role/content 형식의 메시지 배열</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>stream</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>control_scope</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>텍스트 대화. stream은 불리언이며 기본값은 false입니다.</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>output_modalities</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>hosted_operations</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>false</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>multimodal_input_binding</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr></tbody></table></div><p>메서드 별칭: <code>/chat/completions</code></p><p>수명 주기: <code>synchronous_or_streamed</code></p><p class=\"note-s\">정확한 모델 ID를 messages와 함께 보내세요.</p><p class=\"note-s\">컨텍스트 길이는 출력 상한이 아닙니다.</p><p class=\"note-s\">텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>요금 정보는 요청 옵션을 추가하지 않습니다. 지원되는 매개변수는 선택한 메서드에 표시됩니다.</p><dl data-price-conditions><dt>빠른 모드</dt><dd>표준 요금 <span class=\"note-s\">빠른 모드를 선택한 경우</span></dd><dt>Flex 모드</dt><dd>표준 요금 <span class=\"note-s\">flex 모드를 선택한 경우</span></dd><dt>최대 추론 수준</dt><dd>표준 요금 <span class=\"note-s\">최대 추론 수준에 default 조정값을 적용하는 경우</span></dd><dt>추론 수준 · 높음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 높음인 경우</span></dd><dt>추론 수준 · 낮음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 낮음인 경우</span></dd><dt>추론 수준 · 최대</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 최대인 경우</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot 요금</h4><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>토큰의 기본 단가</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot Ultra · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-693-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-693-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-693-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-693-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-693-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-693-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;:&quot;glm-5.3-flash&quot;,&quot;messages&quot;:[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;hello&quot;}],&quot;stream&quot;:false}&#39;)\n\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nr=json.loads(Path(&quot;result.json&quot;).read_text())\nfor x in r.get(&quot;choices&quot;,[]):\n    if x.get(&quot;message&quot;,{}).get(&quot;content&quot;): print(x[&quot;message&quot;][&quot;content&quot;])\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-693-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-693-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nresult=client.chat.completions.create(model=&quot;glm-5.3-flash&quot;, messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;hello&quot;}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(result.to_dict(mode=&quot;json&quot;))\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot Ultra · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5.3-flash",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-5.3-flash",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|chat|/v1/chat/completions|glm-5.3-flash",
      "ordinal": 3,
      "rawMethod": {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "Send the conversation as text messages. Stream must be a boolean; omitted stream defaults to false."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string",
                "when": "텍스트 대화"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Text conversation at the exact model ID and method path.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "정확한 모델 ID를 messages와 함께 보내세요.",
            "컨텍스트 길이는 출력 상한이 아닙니다.",
            "텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "텍스트 대화. stream은 불리언이며 기본값은 false입니다.",
            "file_material": "실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "role/content 형식의 메시지 배열",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [
            "/chat/completions"
          ],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\":\"glm-5.3-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}],\"stream\":false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model=\"glm-5.3-flash\", messages=[{\"role\":\"user\",\"content\":\"hello\"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [
          "/chat/completions"
        ],
        "out": 1,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Standard rate",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Standard rate",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Standard rate",
            "when": "When maximum reasoning effort uses the default adjustment"
          },
          {
            "label": "Reasoning effort · high",
            "value": "Standard rate",
            "when": "When reasoning effort is high"
          },
          {
            "label": "Reasoning effort · low",
            "value": "Standard rate",
            "when": "When reasoning effort is low"
          },
          {
            "label": "Reasoning effort · max",
            "value": "Standard rate",
            "when": "When reasoning effort is max"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|messages|/v1/messages|glm-5.3-flash\" selected>glm-5.3-flash</option><option value=\"Ultra|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option><option value=\"Ultra|messages|/v1/messages|~z-ai%2Fglm-flash-latest\">~z-ai/glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-4\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>json · sse</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>json</code>, <code>sse</code></dd></div><div><dt>출력 형식</dt><dd>JSON 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF-8 텍스트</p><p class=\"note-s\"><code>messages[].content 문자열</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>stream</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요.</td></tr></tbody></table></div><p>수명 주기: <code>synchronous_or_streamed</code></p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>요금 정보는 요청 옵션을 추가하지 않습니다. 지원되는 매개변수는 선택한 메서드에 표시됩니다.</p><dl data-price-conditions><dt>빠른 모드</dt><dd>표준 요금 <span class=\"note-s\">빠른 모드를 선택한 경우</span></dd><dt>Flex 모드</dt><dd>표준 요금 <span class=\"note-s\">flex 모드를 선택한 경우</span></dd><dt>최대 추론 수준</dt><dd>표준 요금 <span class=\"note-s\">최대 추론 수준에 default 조정값을 적용하는 경우</span></dd><dt>추론 수준 · 높음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 높음인 경우</span></dd><dt>추론 수준 · 낮음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 낮음인 경우</span></dd><dt>추론 수준 · 최대</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 최대인 경우</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot 요금</h4><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>토큰의 기본 단가</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot Ultra · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-694-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-694-panel-0\" aria-selected=\"true\" tabindex=\"0\">최소 구성의 완전한 JSON 본문</button><button class=\"cg-tab\" id=\"model-code-694-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-694-panel-1\" aria-selected=\"false\" tabindex=\"-1\">curl · 자신의 UTF-8 문서 사용</button><button class=\"cg-tab\" id=\"model-code-694-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-694-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python · 결과 전체 저장</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-694-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-694-tab-0\"><pre data-lang=\"json\"><code>{\n  &quot;model&quot;: &quot;glm-5.3-flash&quot;,\n  &quot;max_tokens&quot;: 128,\n  &quot;messages&quot;: [\n    {\n      &quot;role&quot;: &quot;user&quot;,\n      &quot;content&quot;: &quot;Summarize the incident report.&quot;\n    }\n  ],\n  &quot;stream&quot;: false\n}</code></pre></div><div class=\"cg-pane\" id=\"model-code-694-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-694-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;glm-5.3-flash&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nPath(&#39;request.json&#39;).write_text(json.dumps(payload, ensure_ascii=False), encoding=&#39;utf-8&#39;)\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-694-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-694-tab-2\" hidden><pre data-lang=\"python\"><code>import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;glm-5.3-flash&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ[&#39;AILOOT_API_KEY&#39;]\nif not api_key.strip():\n    raise SystemExit(&#39;Set AILOOT_API_KEY before making a request&#39;)\nheaders = {&#39;x-api-key&#39;: &#39;PLACEHOLDER_KEY&#39;, &#39;anthropic-version&#39;: &#39;2023-06-01&#39;, &#39;Content-Type&#39;: &#39;application/json&#39;}\nheaders[&#39;x-api-key&#39;] = api_key\nrequest = Request(&#39;https://api.ailoot.ai/v1/messages&#39;, data=json.dumps(payload, ensure_ascii=False).encode(&#39;utf-8&#39;), headers=headers, method=&#39;POST&#39;)\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path(&#39;response-headers.txt&#39;).write_text(str(response.headers), encoding=&#39;utf-8&#39;)\nexcept HTTPError as error:\n    Path(&#39;result.json&#39;).write_bytes(error.read())\n    Path(&#39;response-headers.txt&#39;).write_text(str(error.headers), encoding=&#39;utf-8&#39;)\n    raise\nPath(&#39;result.json&#39;).write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot Ultra · Anthropic Messages</h4><p class=\"note-s\">JSON 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5.3-flash",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-5.3-flash",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|messages|/v1/messages|glm-5.3-flash",
      "ordinal": 4,
      "rawMethod": {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "glm-5.3-flash",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 문자열",
                "required_material": "UTF-8 텍스트"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "protocol",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "JSON 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "glm-5.3-flash"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "glm-5.3-flash",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"glm-5.3-flash\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "messages",
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Standard rate",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Standard rate",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Standard rate",
            "when": "When maximum reasoning effort uses the default adjustment"
          },
          {
            "label": "Reasoning effort · high",
            "value": "Standard rate",
            "when": "When reasoning effort is high"
          },
          {
            "label": "Reasoning effort · low",
            "value": "Standard rate",
            "when": "When reasoning effort is low"
          },
          {
            "label": "Reasoning effort · max",
            "value": "Standard rate",
            "when": "When reasoning effort is max"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.5</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-4.5\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\" selected>glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.5</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-695-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-695-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-695-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-695-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-695-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-695-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-695-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-695-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-695-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-695-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-695-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-695-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-695-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-695-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image&quot;,&quot;source&quot;:{&quot;type&quot;:&quot;base64&quot;,&quot;media_type&quot;:mime,&quot;data&quot;:b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-695-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-695-tab-2\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-4.5&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-695-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-695-tab-3\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-4.5&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-695-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-695-tab-4\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-4.5&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.5",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-4.5",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-4.5",
      "ordinal": 5,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.5\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.5\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.5',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.5</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-4.5\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\" selected>glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\">glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\">glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\">glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\">glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.5</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:input_image,image_url}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-696-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-696-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-696-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-696-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-696-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-696-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-696-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-696-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-696-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-696-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-696-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-696-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-696-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-696-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5&quot;, &quot;input&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;input_text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;input&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;input_image&quot;,&quot;image_url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-696-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-696-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-4.5&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-696-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-696-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-4.5&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-696-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-696-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-4.5&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.5",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-4.5",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-4.5",
      "ordinal": 6,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.5\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.5\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.5\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.5</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-4.5\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\" selected>glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.5</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image_url,image_url:{url,detail}}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-697-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-697-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-697-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-697-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-697-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-697-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-697-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-697-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-697-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-697-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-697-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-697-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-697-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-697-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image_url&quot;,&quot;image_url&quot;:{&quot;url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-697-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-697-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-4.5&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-697-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-697-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-4.5&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-697-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-697-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-4.5&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.5",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-4.5",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-4.5",
      "ordinal": 7,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.5\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.5\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.5',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.5-air</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-4.5-air\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\" selected>glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.5-air</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-698-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-698-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-698-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-698-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-698-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-698-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-698-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-698-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-698-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-698-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-698-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-698-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5-air&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-698-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-698-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5-air&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image&quot;,&quot;source&quot;:{&quot;type&quot;:&quot;base64&quot;,&quot;media_type&quot;:mime,&quot;data&quot;:b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-698-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-698-tab-2\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-4.5-air&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-698-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-698-tab-3\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-4.5-air&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-698-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-698-tab-4\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-4.5-air&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.5-air",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-4.5-air",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-4.5-air",
      "ordinal": 8,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5-air"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.5-air\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.5-air\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.5-air',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5-air",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.5-air</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-4.5-air\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\">glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\" selected>glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\">glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\">glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\">glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\">glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.5-air</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:input_image,image_url}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-699-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-699-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-699-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-699-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-699-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-699-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-699-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-699-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-699-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-699-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-699-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-699-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5-air&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-699-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-699-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5-air&quot;, &quot;input&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;input_text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;input&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;input_image&quot;,&quot;image_url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-699-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-699-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-4.5-air&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-699-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-699-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-4.5-air&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-699-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-699-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-4.5-air&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.5-air",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-4.5-air",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-4.5-air",
      "ordinal": 9,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5-air"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.5-air\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.5-air\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.5-air\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5-air",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.5-air</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-4.5-air\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\" selected>glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.5-air</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image_url,image_url:{url,detail}}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-700-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-700-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-700-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-700-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-700-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-700-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-700-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-700-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-700-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-700-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-700-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-700-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5-air&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-700-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-700-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.5-air&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image_url&quot;,&quot;image_url&quot;:{&quot;url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-700-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-700-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-4.5-air&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-700-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-700-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-4.5-air&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-700-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-700-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-4.5-air&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.5-air",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-4.5-air",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-4.5-air",
      "ordinal": 10,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5-air"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.5-air\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.5-air\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.5-air',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5-air",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.6</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-4.6\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\" selected>glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.6</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-701-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-701-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-701-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-701-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-701-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-701-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-701-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-701-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-701-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-701-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-701-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-701-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.6&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-701-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-701-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.6&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image&quot;,&quot;source&quot;:{&quot;type&quot;:&quot;base64&quot;,&quot;media_type&quot;:mime,&quot;data&quot;:b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-701-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-701-tab-2\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-4.6&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-701-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-701-tab-3\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-4.6&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-701-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-701-tab-4\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-4.6&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.6",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-4.6",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-4.6",
      "ordinal": 11,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.6"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.6\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.6\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.6',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.6",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.6</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-4.6\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\">glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\" selected>glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\">glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\">glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\">glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.6</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:input_image,image_url}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-702-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-702-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-702-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-702-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-702-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-702-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-702-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-702-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-702-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-702-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-702-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-702-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.6&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-702-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-702-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.6&quot;, &quot;input&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;input_text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;input&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;input_image&quot;,&quot;image_url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-702-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-702-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-4.6&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-702-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-702-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-4.6&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-702-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-702-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-4.6&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.6",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-4.6",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-4.6",
      "ordinal": 12,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.6"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.6\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.6\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.6\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.6",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.6</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-4.6\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\" selected>glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.6</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image_url,image_url:{url,detail}}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-703-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-703-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-703-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-703-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-703-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-703-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-703-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-703-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-703-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-703-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-703-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-703-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.6&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-703-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-703-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.6&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image_url&quot;,&quot;image_url&quot;:{&quot;url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-703-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-703-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-4.6&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-703-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-703-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-4.6&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-703-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-703-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-4.6&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.6",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-4.6",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-4.6",
      "ordinal": 13,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.6"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.6\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.6\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.6',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.6",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.7</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-4.7\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\" selected>glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.7</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-704-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-704-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-704-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-704-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-704-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-704-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-704-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-704-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-704-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-704-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.7&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-704-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-704-tab-1\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-4.7&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-704-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-704-tab-2\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-4.7&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-704-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-704-tab-3\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-4.7&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.7",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-4.7",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-4.7",
      "ordinal": 14,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.7"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.7\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.7\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.7\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.7',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.7",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.7</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-4.7\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\">glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\">glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\" selected>glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\">glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\">glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.7</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-705-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-705-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-705-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-705-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-705-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-705-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-705-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-705-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-705-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-705-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.7&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-705-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-705-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-4.7&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-705-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-705-tab-2\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-4.7&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-705-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-705-tab-3\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-4.7&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.7",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-4.7",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-4.7",
      "ordinal": 15,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.7"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.7\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.7\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.7\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.7\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.7",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-4.7</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-4.7\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\" selected>glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-4.7</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-706-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-706-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-706-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-706-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-706-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-706-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-706-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-706-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-706-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-706-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-4.7&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-706-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-706-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-4.7&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-706-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-706-tab-2\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-4.7&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-706-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-706-tab-3\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-4.7&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-4.7",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-4.7",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-4.7",
      "ordinal": 16,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.7"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.7\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.7\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.7\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.7',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.7",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5-turbo</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5-turbo\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\" selected>glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5-turbo</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-707-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-707-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-707-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-707-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-707-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-707-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-707-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-707-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-707-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-707-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-707-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-707-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5-turbo&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-707-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-707-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5-turbo&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image&quot;,&quot;source&quot;:{&quot;type&quot;:&quot;base64&quot;,&quot;media_type&quot;:mime,&quot;data&quot;:b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-707-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-707-tab-2\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-5-turbo&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-707-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-707-tab-3\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-5-turbo&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-707-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-707-tab-4\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-5-turbo&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5-turbo",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-5-turbo",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-5-turbo",
      "ordinal": 17,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5-turbo"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-5-turbo\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-5-turbo\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-5-turbo',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5-turbo",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5-turbo</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5-turbo\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\">glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\">glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\">glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\" selected>glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\">glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\">glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5-turbo</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:input_image,image_url}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-708-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-708-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-708-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-708-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-708-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-708-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-708-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-708-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-708-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-708-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-708-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-708-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5-turbo&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-708-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-708-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5-turbo&quot;, &quot;input&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;input_text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;input&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;input_image&quot;,&quot;image_url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-708-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-708-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-5-turbo&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-708-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-708-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-5-turbo&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-708-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-708-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-5-turbo&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5-turbo",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-5-turbo",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-5-turbo",
      "ordinal": 18,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5-turbo"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-5-turbo\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-5-turbo\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-5-turbo\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5-turbo",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-5-turbo</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5-turbo\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\" selected>glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-5-turbo</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image_url,image_url:{url,detail}}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-709-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-709-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-709-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-709-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-709-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-709-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-709-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-709-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-709-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-709-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-709-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-709-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5-turbo&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-709-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-709-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-5-turbo&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image_url&quot;,&quot;image_url&quot;:{&quot;url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-709-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-709-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-5-turbo&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-709-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-709-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-5-turbo&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-709-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-709-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-5-turbo&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-5-turbo",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-5-turbo",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-5-turbo",
      "ordinal": 19,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5-turbo"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-5-turbo\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-5-turbo\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-5-turbo',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5-turbo",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\" selected>glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-710-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-710-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-710-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-710-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-710-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-710-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-710-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-710-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-710-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-710-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-710-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-710-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-710-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-710-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image&quot;,&quot;source&quot;:{&quot;type&quot;:&quot;base64&quot;,&quot;media_type&quot;:mime,&quot;data&quot;:b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-710-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-710-tab-2\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-flash&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-710-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-710-tab-3\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-flash&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-710-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-710-tab-4\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-flash&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-flash",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-flash",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-flash",
      "ordinal": 20,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-flash\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-flash\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-flash',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\">glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\">glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\">glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\" selected>glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\">glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:input_image,image_url}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-711-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-711-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-711-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-711-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-711-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-711-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-711-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-711-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-711-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-711-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-711-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-711-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-711-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-711-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash&quot;, &quot;input&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;input_text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;input&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;input_image&quot;,&quot;image_url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-711-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-711-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-flash&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-711-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-711-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-flash&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-711-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-711-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-flash&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-flash",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-flash",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-flash",
      "ordinal": 21,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-flash\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\" selected>glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image_url,image_url:{url,detail}}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-712-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-712-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-712-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-712-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-712-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-712-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-712-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-712-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-712-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-712-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-712-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-712-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-712-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-712-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image_url&quot;,&quot;image_url&quot;:{&quot;url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-712-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-712-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-flash&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-712-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-712-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-flash&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-712-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-712-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-flash&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-flash",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-flash",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-flash",
      "ordinal": 22,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-flash\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-flash\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-flash-latest</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-flash-latest\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\" selected>glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-flash-latest</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-713-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-713-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-713-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-713-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-713-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-713-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-713-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-713-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-713-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-713-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-713-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-713-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash-latest&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-713-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-713-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash-latest&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image&quot;,&quot;source&quot;:{&quot;type&quot;:&quot;base64&quot;,&quot;media_type&quot;:mime,&quot;data&quot;:b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-713-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-713-tab-2\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;glm-flash-latest&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-713-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-713-tab-3\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;glm-flash-latest&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-713-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-713-tab-4\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;glm-flash-latest&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-flash-latest",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "glm-flash-latest",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|glm-flash-latest",
      "ordinal": 23,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-flash-latest\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-flash-latest\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-flash-latest',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-flash-latest</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-flash-latest\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|responses|/v1/responses|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|responses|/v1/responses|glm-4.5\">glm-4.5</option><option value=\"Core|responses|/v1/responses|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|responses|/v1/responses|glm-4.6\">glm-4.6</option><option value=\"Core|responses|/v1/responses|glm-4.7\">glm-4.7</option><option value=\"Core|responses|/v1/responses|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|responses|/v1/responses|glm-flash\">glm-flash</option><option value=\"Core|responses|/v1/responses|glm-flash-latest\" selected>glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-2\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Responses</b> <code>POST /v1/responses</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-flash-latest</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|input_item[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>message, reasoning, function_call, function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output. 실제 반환된 call_id를 유지하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">input[].output</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: function_call_output</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_output_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning.summary</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">text.verbosity</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">include</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">store</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">previous_response_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>ID 요건: 지원되는 이어가기의 실제 응답 ID만 사용</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_key</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>입력 텍스트 또는 input_text 파트</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:input_image,image_url}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, input</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Responses</b><code>POST /v1/responses</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Responses</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-714-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-714-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-714-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-714-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-714-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-714-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-714-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-714-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-714-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-714-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-714-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-714-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash-latest&quot;, &quot;input&quot;: &quot;&quot;}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;input&quot;]=&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-714-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-714-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash-latest&quot;, &quot;input&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;input_text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;input&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;input_image&quot;,&quot;image_url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(json.loads(Path(&quot;result.json&quot;).read_text(encoding=&quot;utf-8&quot;)))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-714-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-714-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.responses.create(model=&quot;glm-flash-latest&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-714-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-714-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: &quot;glm-flash-latest&quot;, input: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; });\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-714-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-714-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nwith client.responses.stream(model=&quot;glm-flash-latest&quot;, input=&quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Responses</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">status</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>message|reasoning|function_call|other item</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output[].content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>content part</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=responses\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=responses\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=responses\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=responses\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=responses\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=responses\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=responses\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=responses\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-flash-latest",
        "fmt": "responses",
        "http": "POST",
        "path": "/v1/responses",
        "request_model_id": "glm-flash-latest",
        "route_label": "Core"
      },
      "method_key": "Core|responses|/v1/responses|glm-flash-latest",
      "ordinal": 24,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-flash-latest\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-flash-latest\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-flash-latest\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>glm-flash-latest</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-flash-latest\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\" selected>glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트 · 이미지</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code>, <code>image</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,000,000 tokens</dd></div><div><dt>최대 출력</dt><dd>131,072 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>glm-flash-latest</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p><p class=\"note-s\"><b>텍스트 + 이미지</b></p><p class=\"note-s\"><code>{type:image_url,image_url:{url,detail}}</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text, image</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-715-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-715-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-715-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-715-panel-1\" aria-selected=\"false\" tabindex=\"-1\">입력, 이미지</button><button class=\"cg-tab\" id=\"model-code-715-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-715-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-715-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-715-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-715-tab-4\" role=\"tab\" type=\"button\" aria-controls=\"model-code-715-panel-4\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-715-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-715-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash-latest&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-715-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-715-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}&quot;\nexport AILOOT_IMAGE_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;glm-flash-latest&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: [{&quot;type&quot;: &quot;text&quot;, &quot;text&quot;: &quot;Read labels and numbers in this image; flag unreadable text.&quot;}]}]}&#39;)\nimport base64\nf=Path(os.environ[&quot;AILOOT_IMAGE_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose an actual PNG JPEG or WebP image&quot;)\nraw=f.read_bytes()\nmime=&quot;image/png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;image/jpeg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;image/webp&quot; if raw[:4]==b&quot;RIFF&quot; and raw[8:12]==b&quot;WEBP&quot; else None\nif not mime:raise SystemExit(&quot;Use PNG JPEG or WebP&quot;)\nb64=base64.b64encode(raw).decode()\np[&quot;messages&quot;][0][&quot;content&quot;].append({&quot;type&quot;:&quot;image_url&quot;,&quot;image_url&quot;:{&quot;url&quot;:&quot;data:&quot;+mime+&quot;;base64,&quot;+b64}})\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-715-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-715-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;glm-flash-latest&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-715-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-715-tab-3\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;glm-flash-latest&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-715-panel-4\" role=\"tabpanel\" aria-labelledby=\"model-code-715-tab-4\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;glm-flash-latest&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "glm-flash-latest",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "glm-flash-latest",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|glm-flash-latest",
      "ordinal": 25,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-flash-latest\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-flash-latest\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-flash-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>z-ai/glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|messages|/v1/messages|glm-4.5\">glm-4.5</option><option value=\"Core|messages|/v1/messages|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|messages|/v1/messages|glm-4.6\">glm-4.6</option><option value=\"Core|messages|/v1/messages|glm-4.7\">glm-4.7</option><option value=\"Core|messages|/v1/messages|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|messages|/v1/messages|glm-flash\">glm-flash</option><option value=\"Core|messages|/v1/messages|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash\" selected>z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-1\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>1,048,576 tokens</dd></div><div><dt>최대 출력</dt><dd>32,768 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>z-ai/glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">system</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_block[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div>한도 적용 대상: 선택한 모델/카드의 정확한 상한</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_sequences</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].input_schema</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">thinking.budget_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">output_config.effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">metadata</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content 또는 type=text 블록</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> Anthropic Messages</b><code>POST /v1/messages</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div><div><dt>캐시 쓰기</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>캐시 쓰기, 5분</dt><dd>US$0.00015 <em>/ 1K tokens</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-716-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-716-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-716-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-716-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-716-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-716-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-716-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-716-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-716-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-716-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;z-ai/glm-5.3-flash&quot;, &quot;max_tokens&quot;: 1024, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-716-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-716-tab-1\" hidden><pre data-lang=\"python\"><code>import anthropic\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nmsg = client.messages.create(\n    model=&quot;z-ai/glm-5.3-flash&quot;,\n    max_tokens=1024,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(msg.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-716-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-716-tab-2\" hidden><pre data-lang=\"js\"><code>import Anthropic from &quot;@anthropic-ai/sdk&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new Anthropic({ baseURL: &quot;https://api.ailoot.ai&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: &quot;z-ai/glm-5.3-flash&quot;,\n  max_tokens: 1024,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-716-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-716-tab-3\" hidden><pre data-lang=\"python\"><code>import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=anthropic.Anthropic(base_url=&quot;https://api.ailoot.ai&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.messages.stream(model=&#39;z-ai/glm-5.3-flash&#39;,max_tokens=1024,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · Anthropic Messages</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "z-ai/glm-5.3-flash",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Core"
      },
      "method_key": "Core|messages|/v1/messages|z-ai%2Fglm-5.3-flash",
      "ordinal": 26,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": 0.15,
        "cache_write_1h": null,
        "cache_write_5m": 0.15,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1048576,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"z-ai/glm-5.3-flash\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"z-ai/glm-5.3-flash\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"z-ai/glm-5.3-flash\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='z-ai/glm-5.3-flash',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": 32768,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>z-ai/glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5\">glm-4.5</option><option value=\"Core|chat|/v1/chat/completions|glm-4.5-air\">glm-4.5-air</option><option value=\"Core|chat|/v1/chat/completions|glm-4.6\">glm-4.6</option><option value=\"Core|chat|/v1/chat/completions|glm-4.7\">glm-4.7</option><option value=\"Core|chat|/v1/chat/completions|glm-5-turbo\">glm-5-turbo</option><option value=\"Core|chat|/v1/chat/completions|glm-flash\">glm-flash</option><option value=\"Core|chat|/v1/chat/completions|glm-flash-latest\">glm-flash-latest</option><option value=\"Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\" selected>z-ai/glm-5.3-flash</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>컨텍스트</dt><dd>4,096 tokens</dd></div><div><dt>최대 출력</dt><dd>1,024 tokens</dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>z-ai/glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다</td></tr></tbody></table></div><p>수명 주기: <code>exact retained published method</code></p><p class=\"note-s\">메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><h4>Ailoot 메서드 요금</h4><section class=\"meth\" data-route=\"Core\"><header><b><span class=\"alias\">Ailoot</span> OpenAI Chat</b><code>POST /v1/chat/completions</code></header><dl><div><dt>입력</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>출력</dt><dd>US$0.0005 <em>/ 1K</em></dd></div><div><dt>캐시 읽기</dt><dd>≈US$0.00003 <em>/ 1K</em></dd></div><div><dt>캐시 쓰기</dt><dd>US$0.00015 <em>/ 1K</em></dd></div><div><dt>캐시 쓰기, 5분</dt><dd>US$0.00015 <em>/ 1K tokens</em></dd></div></dl></section><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p><div data-model-tariff-reference><h4>참조 요금 상세 정보</h4><p class=\"note-s\">모델 수준의 참조 요금표는 메서드 선택, 견적 또는 요금을 변경하지 않습니다. 실제 과금에는 선택한 Ailoot 메서드 요금이 적용됩니다.</p><details class=\"card-price-reference\" data-profile-scope=\"model_reference\" data-client-selectable=\"false\"><summary>모델 참조 요금표</summary><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>OpenAI Chat · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 기본 토큰 요금</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>Anthropic Messages · 요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-717-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-717-panel-0\" aria-selected=\"true\" tabindex=\"0\">텍스트 예제</button><button class=\"cg-tab\" id=\"model-code-717-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-717-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-717-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-717-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Node.js SDK</button><button class=\"cg-tab\" id=\"model-code-717-tab-3\" role=\"tab\" type=\"button\" aria-controls=\"model-code-717-panel-3\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-717-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-717-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;z-ai/glm-5.3-flash&quot;, &quot;messages&quot;: []}&#39;)\nf=Path(os.environ[&quot;AILOOT_TEXT_FILE&quot;])\nif not f.is_file():raise SystemExit(&quot;Choose your actual UTF-8 source material&quot;)\ntext=f.read_text(encoding=&quot;utf-8&quot;)\nif not text.strip():raise SystemExit(&quot;Source material must contain text&quot;)\np[&quot;messages&quot;]=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Summarize this material and quote supporting source passages.\\n\\n&quot;+text}]\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(&quot;result.json&quot;).read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-717-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-717-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient = OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;, api_key=os.environ[&quot;AILOOT_API_KEY&quot;], max_retries=0)\nresp = client.chat.completions.create(\n    model=&quot;z-ai/glm-5.3-flash&quot;,\n    messages=[{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(resp.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-717-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-717-tab-2\" hidden><pre data-lang=\"js\"><code>import OpenAI from &quot;openai&quot;;\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(&quot;Set AILOOT_API_KEY before making a request&quot;);\nconst client = new OpenAI({ baseURL: &quot;https://api.ailoot.ai/v1&quot;, apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: &quot;z-ai/glm-5.3-flash&quot;,\n  messages: [{ role: &quot;user&quot;, content: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot; }],\n});\nimport { writeFileSync } from &quot;node:fs&quot;;\n\nfunction saveResult(data, stem = &quot;result&quot;) {\n  writeFileSync(stem + &quot;.json&quot;, JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) =&gt; {\n    const raw = Buffer.from(encoded, &quot;base64&quot;);\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? &quot;png&quot; : raw[0]===255 &amp;&amp; raw[1]===216 ? &quot;jpg&quot; : raw.subarray(0,4).toString()===&quot;RIFF&quot; &amp;&amp; raw.subarray(8,12).toString()===&quot;WEBP&quot; ? &quot;webp&quot; : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(&quot;Saved&quot;, file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(&quot;Content&quot;, i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(&quot;Choice&quot;, choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(&quot;Output&quot;, i, JSON.stringify(item));\n    if (item.type === &quot;image_generation_call&quot; &amp;&amp; item.result) saveBlob(item.result, item.output_format || &quot;bin&quot;, `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(&quot;Candidate/part&quot;, ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;})[mime] || &quot;bin&quot;;\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-717-panel-3\" role=\"tabpanel\" aria-labelledby=\"model-code-717-tab-3\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;z-ai/glm-5.3-flash&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "z-ai/glm-5.3-flash",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Core"
      },
      "method_key": "Core|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash",
      "ordinal": 27,
      "rawMethod": {
        "cache_read": 0.03,
        "cache_write": 0.15,
        "cache_write_1h": null,
        "cache_write_5m": 0.15,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"z-ai/glm-5.3-flash\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"z-ai/glm-5.3-flash\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"z-ai/glm-5.3-flash\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='z-ai/glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>z-ai/glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Ultra|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\" selected>z-ai/glm-5.3-flash</option><option value=\"Ultra|chat|/v1/chat/completions|~z-ai%2Fglm-flash-latest\">~z-ai/glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-3\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>z-ai/glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>function</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">modalities</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>text</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>조건: 이 Ultra 텍스트 경로에서는 provider.options가 거부됩니다</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control.ttl</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>조건: 실제 프롬프트 캐시 지정 위치에서는 1h가 거부됩니다</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>messages</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>role/content 형식의 메시지 배열</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>stream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>control_scope</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>모델별로 다름. 사용자 함수 도구와 호스팅 도구는 서로 다릅니다</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>output_modalities</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>hosted_operations</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>false</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>multimodal_input_binding</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr></tbody></table></div><p>수명 주기: <code>synchronous_or_streamed</code></p><p class=\"note-s\">정확한 모델 ID를 messages와 함께 보내세요.</p><p class=\"note-s\">컨텍스트 길이는 출력 상한이 아닙니다.</p><p class=\"note-s\">텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>요금 정보는 요청 옵션을 추가하지 않습니다. 지원되는 매개변수는 선택한 메서드에 표시됩니다.</p><dl data-price-conditions><dt>빠른 모드</dt><dd>표준 요금 <span class=\"note-s\">빠른 모드를 선택한 경우</span></dd><dt>Flex 모드</dt><dd>표준 요금 <span class=\"note-s\">flex 모드를 선택한 경우</span></dd><dt>최대 추론 수준</dt><dd>표준 요금 <span class=\"note-s\">최대 추론 수준에 default 조정값을 적용하는 경우</span></dd><dt>추론 수준 · 높음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 높음인 경우</span></dd><dt>추론 수준 · 낮음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 낮음인 경우</span></dd><dt>추론 수준 · 최대</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 최대인 경우</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot 요금</h4><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>토큰의 기본 단가</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot Ultra · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-718-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-718-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-718-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-718-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-718-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-718-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-718-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-718-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;z-ai/glm-5.3-flash&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}]}&#39;)\n\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nr=json.loads(Path(&quot;result.json&quot;).read_text())\nfor x in r.get(&quot;choices&quot;,[]):\n    if x.get(&quot;message&quot;,{}).get(&quot;content&quot;): print(x[&quot;message&quot;][&quot;content&quot;])\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-718-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-718-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nresult=client.chat.completions.create(model=&#39;z-ai/glm-5.3-flash&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(result.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-718-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-718-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;z-ai/glm-5.3-flash&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot Ultra · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "z-ai/glm-5.3-flash",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash",
      "ordinal": 28,
      "rawMethod": {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID.",
              "Guarded canonical keys must occur once; duplicate or case-varied model/tools/cap fields are rejected."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": [
                  "function"
                ],
                "enum_known": true,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "text"
                ],
                "enum_known": true,
                "name": "modalities",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "conditions": "이 Ultra 텍스트 경로에서는 provider.options가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "conditions": "실제 프롬프트 캐시 지정 위치에서는 1h가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control.ttl",
                "required": false,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "정확한 모델 ID를 messages와 함께 보내세요.",
            "컨텍스트 길이는 출력 상한이 아닙니다.",
            "텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "모델별로 다름. 사용자 함수 도구와 호스팅 도구는 서로 다릅니다",
            "file_material": "실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "role/content 형식의 메시지 배열",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream",
              "temperature",
              "top_p",
              "stop",
              "max_tokens",
              "max_completion_tokens",
              "reasoning",
              "response_format",
              "tools",
              "tool_choice"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"z-ai/glm-5.3-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model='z-ai/glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='z-ai/glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python SDK streaming · all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "interval_boundary": "min_exclusive_max_inclusive",
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "null_rate_policy": "unknown or inherited; never zero",
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>z-ai/glm-5.3-flash</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Ultra|messages|/v1/messages|z-ai%2Fglm-5.3-flash\" selected>z-ai/glm-5.3-flash</option><option value=\"Ultra|messages|/v1/messages|~z-ai%2Fglm-flash-latest\">~z-ai/glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-4\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>json · sse</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>json</code>, <code>sse</code></dd></div><div><dt>출력 형식</dt><dd>JSON 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>z-ai/glm-5.3-flash</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF-8 텍스트</p><p class=\"note-s\"><code>messages[].content 문자열</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>stream</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요.</td></tr></tbody></table></div><p>수명 주기: <code>synchronous_or_streamed</code></p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>요금 정보는 요청 옵션을 추가하지 않습니다. 지원되는 매개변수는 선택한 메서드에 표시됩니다.</p><dl data-price-conditions><dt>빠른 모드</dt><dd>표준 요금 <span class=\"note-s\">빠른 모드를 선택한 경우</span></dd><dt>Flex 모드</dt><dd>표준 요금 <span class=\"note-s\">flex 모드를 선택한 경우</span></dd><dt>최대 추론 수준</dt><dd>표준 요금 <span class=\"note-s\">최대 추론 수준에 default 조정값을 적용하는 경우</span></dd><dt>추론 수준 · 높음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 높음인 경우</span></dd><dt>추론 수준 · 낮음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 낮음인 경우</span></dd><dt>추론 수준 · 최대</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 최대인 경우</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot 요금</h4><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>토큰의 기본 단가</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot Ultra · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-719-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-719-panel-0\" aria-selected=\"true\" tabindex=\"0\">최소 구성의 완전한 JSON 본문</button><button class=\"cg-tab\" id=\"model-code-719-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-719-panel-1\" aria-selected=\"false\" tabindex=\"-1\">curl · 자신의 UTF-8 문서 사용</button><button class=\"cg-tab\" id=\"model-code-719-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-719-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python · 결과 전체 저장</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-719-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-719-tab-0\"><pre data-lang=\"json\"><code>{\n  &quot;model&quot;: &quot;z-ai/glm-5.3-flash&quot;,\n  &quot;max_tokens&quot;: 128,\n  &quot;messages&quot;: [\n    {\n      &quot;role&quot;: &quot;user&quot;,\n      &quot;content&quot;: &quot;Summarize the incident report.&quot;\n    }\n  ],\n  &quot;stream&quot;: false\n}</code></pre></div><div class=\"cg-pane\" id=\"model-code-719-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-719-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;z-ai/glm-5.3-flash&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nPath(&#39;request.json&#39;).write_text(json.dumps(payload, ensure_ascii=False), encoding=&#39;utf-8&#39;)\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-719-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-719-tab-2\" hidden><pre data-lang=\"python\"><code>import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;z-ai/glm-5.3-flash&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ[&#39;AILOOT_API_KEY&#39;]\nif not api_key.strip():\n    raise SystemExit(&#39;Set AILOOT_API_KEY before making a request&#39;)\nheaders = {&#39;x-api-key&#39;: &#39;PLACEHOLDER_KEY&#39;, &#39;anthropic-version&#39;: &#39;2023-06-01&#39;, &#39;Content-Type&#39;: &#39;application/json&#39;}\nheaders[&#39;x-api-key&#39;] = api_key\nrequest = Request(&#39;https://api.ailoot.ai/v1/messages&#39;, data=json.dumps(payload, ensure_ascii=False).encode(&#39;utf-8&#39;), headers=headers, method=&#39;POST&#39;)\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path(&#39;response-headers.txt&#39;).write_text(str(response.headers), encoding=&#39;utf-8&#39;)\nexcept HTTPError as error:\n    Path(&#39;result.json&#39;).write_bytes(error.read())\n    Path(&#39;response-headers.txt&#39;).write_text(str(error.headers), encoding=&#39;utf-8&#39;)\n    raise\nPath(&#39;result.json&#39;).write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot Ultra · Anthropic Messages</h4><p class=\"note-s\">JSON 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "z-ai/glm-5.3-flash",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|messages|/v1/messages|z-ai%2Fglm-5.3-flash",
      "ordinal": 29,
      "rawMethod": {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "z-ai/glm-5.3-flash",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 문자열",
                "required_material": "UTF-8 텍스트"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "protocol",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "JSON 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "z-ai/glm-5.3-flash"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "z-ai/glm-5.3-flash",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"z-ai/glm-5.3-flash\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'z-ai/glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'z-ai/glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "messages",
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>~z-ai/glm-flash-latest</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|~z-ai%2Fglm-flash-latest\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|glm-5.3-flash\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Ultra|chat|/v1/chat/completions|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option><option value=\"Ultra|chat|/v1/chat/completions|~z-ai%2Fglm-flash-latest\" selected>~z-ai/glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-3\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>텍스트</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · OpenAI Chat</b> <code>POST /v1/chat/completions</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>text</code></dd></div><div><dt>출력 형식</dt><dd>json 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>~z-ai/glm-flash-latest</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최소 항목 수: 1</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>예시: system, user, assistant, tool, function</div><div>조건: 이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|content_part[]|null</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>tool_call[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].tool_call_id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: role=tool. 실제 반환된 ID를 사용하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object|array</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_completion_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>최솟값: 1</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream_options.include_usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">top_p</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>number</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function_tool[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].type</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>function</div><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.name</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>적용 조건: 함수 도구 지정됨</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.description</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tools[].function.parameters</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>JSON_schema</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">tool_choice</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">parallel_tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning_effort</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">reasoning</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">service_tier</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_compatibility\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">instructions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">호환성 필드</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">functions</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>function[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">function_call</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string|object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"model_dependent\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">prompt_cache_options</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div class=\"note-s\">모델에 따라 다름</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">modalities</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>text</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>object</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>조건: 이 Ultra 텍스트 경로에서는 provider.options가 거부됩니다</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">cache_control.ttl</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>조건: 실제 프롬프트 캐시 지정 위치에서는 1h가 거부됩니다</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF8 텍스트</p><p class=\"note-s\"><code>messages[].content</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>messages</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>role/content 형식의 메시지 배열</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>stream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>control_scope</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>모델별로 다름. 사용자 함수 도구와 호스팅 도구는 서로 다릅니다</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>output_modalities</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>hosted_operations</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>false</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>multimodal_input_binding</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>null</td></tr></tbody></table></div><p>수명 주기: <code>synchronous_or_streamed</code></p><p class=\"note-s\">정확한 모델 ID를 messages와 함께 보내세요.</p><p class=\"note-s\">컨텍스트 길이는 출력 상한이 아닙니다.</p><p class=\"note-s\">텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다.</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>요금 정보는 요청 옵션을 추가하지 않습니다. 지원되는 매개변수는 선택한 메서드에 표시됩니다.</p><dl data-price-conditions><dt>빠른 모드</dt><dd>표준 요금 <span class=\"note-s\">빠른 모드를 선택한 경우</span></dd><dt>Flex 모드</dt><dd>표준 요금 <span class=\"note-s\">flex 모드를 선택한 경우</span></dd><dt>최대 추론 수준</dt><dd>표준 요금 <span class=\"note-s\">최대 추론 수준에 default 조정값을 적용하는 경우</span></dd><dt>추론 수준 · 높음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 높음인 경우</span></dd><dt>추론 수준 · 낮음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 낮음인 경우</span></dd><dt>추론 수준 · 최대</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 최대인 경우</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot 요금</h4><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>토큰의 기본 단가</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot Ultra · OpenAI Chat</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-720-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-720-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl</button><button class=\"cg-tab\" id=\"model-code-720-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-720-panel-1\" aria-selected=\"false\" tabindex=\"-1\">Python SDK</button><button class=\"cg-tab\" id=\"model-code-720-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-720-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python 스트리밍</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-720-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-720-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\np=json.loads(&#39;{&quot;model&quot;: &quot;~z-ai/glm-flash-latest&quot;, &quot;messages&quot;: [{&quot;role&quot;: &quot;user&quot;, &quot;content&quot;: &quot;Explain the difference between an observation and a hypothesis in three sentences.&quot;}]}&#39;)\n\nPath(&quot;request.json&quot;).write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\nr=json.loads(Path(&quot;result.json&quot;).read_text())\nfor x in r.get(&quot;choices&quot;,[]):\n    if x.get(&quot;message&quot;,{}).get(&quot;content&quot;): print(x[&quot;message&quot;][&quot;content&quot;])\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-720-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-720-tab-1\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nresult=client.chat.completions.create(model=&#39;~z-ai/glm-flash-latest&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nsave_result(result.to_dict(mode=&quot;json&quot;))\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-720-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-720-tab-2\" hidden><pre data-lang=\"python\"><code>from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(&quot;AILOOT_API_KEY&quot;, &quot;&quot;).strip(): raise SystemExit(&quot;Set AILOOT_API_KEY before making a request&quot;)\nclient=OpenAI(base_url=&quot;https://api.ailoot.ai/v1&quot;,api_key=os.environ[&quot;AILOOT_API_KEY&quot;],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=&quot;result&quot;):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + &quot;.json&quot;).write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=&quot;utf-8&quot;)\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b&quot;-_&quot;, validate=True)\n        ext = &quot;png&quot; if raw.startswith(b&quot;\\x89PNG\\r\\n\\x1a\\n&quot;) else &quot;jpg&quot; if raw.startswith(b&quot;\\xff\\xd8&quot;) else &quot;webp&quot; if raw[:4] == b&quot;RIFF&quot; and raw[8:12] == b&quot;WEBP&quot; else suffix\n        file = Path(stem + &quot;-&quot; + label + &quot;.&quot; + ext)\n        file.write_bytes(raw)\n        print(&quot;Saved&quot;, file)\n    for index, block in enumerate(data.get(&quot;content&quot;) or []):\n        print(&quot;Content&quot;, index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(&quot;choices&quot;) or []:\n        print(&quot;Choice&quot;, choice.get(&quot;index&quot;), json.dumps(choice.get(&quot;message&quot;, choice.get(&quot;delta&quot;, {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(&quot;output&quot;) or []):\n        print(&quot;Output&quot;, index, json.dumps(item, ensure_ascii=False))\n        if item.get(&quot;type&quot;) == &quot;image_generation_call&quot; and item.get(&quot;result&quot;):\n            save_blob(item[&quot;result&quot;], item.get(&quot;output_format&quot;) or &quot;bin&quot;, &quot;output-&quot; + str(index))\n    for ci, candidate in enumerate(data.get(&quot;candidates&quot;) or []):\n        for pi, part in enumerate((candidate.get(&quot;content&quot;) or {}).get(&quot;parts&quot;) or []):\n            print(&quot;Candidate/part&quot;, ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(&quot;inlineData&quot;) or part.get(&quot;inline_data&quot;)\n            if blob and blob.get(&quot;data&quot;):\n                mime = blob.get(&quot;mimeType&quot;) or blob.get(&quot;mime_type&quot;)\n                suffix = {&quot;image/png&quot;:&quot;png&quot;, &quot;image/jpeg&quot;:&quot;jpg&quot;, &quot;image/webp&quot;:&quot;webp&quot;, &quot;audio/wav&quot;:&quot;wav&quot;, &quot;audio/mpeg&quot;:&quot;mp3&quot;, &quot;video/mp4&quot;:&quot;mp4&quot;}.get(mime, &quot;bin&quot;)\n                save_blob(blob[&quot;data&quot;], suffix, &quot;candidate-&quot; + str(ci) + &quot;-part-&quot; + str(pi))\n\nwith client.chat.completions.stream(model=&#39;~z-ai/glm-flash-latest&#39;,messages=[{&quot;role&quot;:&quot;user&quot;,&quot;content&quot;:&quot;Explain observations and hypotheses in three sentences.&quot;}]) as stream:\n    with Path(&quot;stream-events.jsonl&quot;).open(&quot;w&quot;,encoding=&quot;utf-8&quot;) as log:\n        for event in stream:\n            payload=event.to_dict(mode=&quot;json&quot;)\n            log.write(json.dumps(payload,ensure_ascii=False)+&quot;\\n&quot;); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=&quot;json&quot;),&quot;stream-result&quot;)\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot Ultra · OpenAI Chat</h4><p class=\"note-s\">json 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].index</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>integer</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.tool_calls</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>tool_call[]</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].message.reasoning_details</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object|array</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">choices[].finish_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=chat\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=chat\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=chat\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=chat\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=chat\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=chat\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=chat\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=chat\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=chat\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=chat\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "~z-ai/glm-flash-latest",
        "fmt": "chat",
        "http": "POST",
        "path": "/v1/chat/completions",
        "request_model_id": "~z-ai/glm-flash-latest",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|chat|/v1/chat/completions|~z-ai%2Fglm-flash-latest",
      "ordinal": 30,
      "rawMethod": {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID.",
              "Guarded canonical keys must occur once; duplicate or case-varied model/tools/cap fields are rejected."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "~z-ai/glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": [
                  "function"
                ],
                "enum_known": true,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "text"
                ],
                "enum_known": true,
                "name": "modalities",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "conditions": "이 Ultra 텍스트 경로에서는 provider.options가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "conditions": "실제 프롬프트 캐시 지정 위치에서는 1h가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control.ttl",
                "required": false,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "정확한 모델 ID를 messages와 함께 보내세요.",
            "컨텍스트 길이는 출력 상한이 아닙니다.",
            "텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "모델별로 다름. 사용자 함수 도구와 호스팅 도구는 서로 다릅니다",
            "file_material": "실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "role/content 형식의 메시지 배열",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream",
              "temperature",
              "top_p",
              "stop",
              "max_tokens",
              "max_completion_tokens",
              "reasoning",
              "response_format",
              "tools",
              "tool_choice"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"~z-ai/glm-flash-latest\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model='~z-ai/glm-flash-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='~z-ai/glm-flash-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python SDK streaming · all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "~z-ai/glm-flash-latest",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "interval_boundary": "min_exclusive_max_inclusive",
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "null_rate_policy": "unknown or inherited; never zero",
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    },
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">Z</span><h2 id=\"sheet-title\">Z.ai: GLM 5.3 Flash</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"닫기\">×</button></div><div class=\"idline\"><span>Z.ai /</span><code>~z-ai/glm-flash-latest</code><button type=\"button\" id=\"copy-id\">ID 복사</button></div><nav class=\"card-jump-nav\" aria-label=\"모델 카드 섹션\"><button type=\"button\" data-card-jump=\"overview\">시작하기</button><button type=\"button\" data-card-jump=\"methods\">입력 및 메서드</button><button type=\"button\" data-card-jump=\"pricing\">요금</button><button type=\"button\" data-card-jump=\"examples\">예제</button><button type=\"button\" data-card-jump=\"results\">결과</button><button type=\"button\" data-card-jump=\"aliases\">별칭</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 메서드\"><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-0\" data-card-method=\"Core|chat|/v1/chat/completions|glm-5.3-flash\">Chat</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-1\" data-card-method=\"Core|messages|/v1/messages|glm-5.3-flash\">Messages</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-2\" data-card-method=\"Core|responses|/v1/responses|glm-5.3-flash\">Responses</button><button type=\"button\" role=\"tab\" tabindex=\"-1\" aria-controls=\"card-method-content\" aria-selected=\"false\" id=\"card-method-tab-3\" data-card-method=\"Ultra|chat|/v1/chat/completions|glm-5.3-flash\">Chat · Ultra</button><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-4\" data-card-method=\"Ultra|messages|/v1/messages|~z-ai%2Fglm-flash-latest\">Messages · Ultra</button></div><div class=\"idline\"><label for=\"card-model-id\">모델 ID</label><select class=\"sel\" id=\"card-model-id\" style=\"min-width:0;max-width:100%\"><option value=\"Ultra|messages|/v1/messages|glm-5.3-flash\">glm-5.3-flash</option><option value=\"Ultra|messages|/v1/messages|z-ai%2Fglm-5.3-flash\">z-ai/glm-5.3-flash</option><option value=\"Ultra|messages|/v1/messages|~z-ai%2Fglm-flash-latest\" selected>~z-ai/glm-flash-latest</option></select></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-4\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">시작하기</h3><p class=\"mdesc-full\">GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.</p><dl class=\"card-io\" data-card-io><div><dt>허용 입력</dt><dd>텍스트</dd></div><div><dt>결과</dt><dd>json · sse</dd></div></dl><details class=\"card-about\"><summary>모델 소개</summary><p class=\"note-s\" data-model-method-boundary>이 설명은 모델의 기능을 다룹니다. Ailoot에서 사용할 수 있는 입력, 출력 및 옵션은 아래에 선택한 메서드별로 표시됩니다.</p><div class=\"mabout\" id=\"m-about\"><h4>작업을 위한 멀티모달 모델</h4><p>GLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.</p><h4>긴 컨텍스트의 아키텍처</h4><p>모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.</p><p>시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.</p><h4>추론, 도구, 데이터</h4><p>추론은 항상 활성화됩니다. 깊이는 <code>low</code>, <code>high</code>, <code>max</code> 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.</p><p>도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.</p><p>반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.</p><h4>시각 지시에 따른 개발</h4><p>모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.</p><h4>문서와 전문 분석</h4><p>프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.</p><p>재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.</p><h4>동영상, 3차원 장면, 인터페이스</h4><p>에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.</p><p>3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.</p><p>이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot에서 사용 가능 · 입력 및 메서드</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · Anthropic Messages</b> <code>POST /v1/messages</code></summary><dl class=\"method-capabilities\"><div><dt>입력</dt><dd><code>text</code></dd></div><div><dt>출력</dt><dd><code>json</code>, <code>sse</code></dd></div><div><dt>출력 형식</dt><dd>JSON 또는 SSE</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>필드</th><th>유형</th><th>요건</th><th>값과 한도</th><th>기본값</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>~z-ai/glm-flash-latest</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>message[]</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].role</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span><div>user, assistant</div></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">messages[].content</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>string</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">max_tokens</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>integer</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>필수</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"unspecified\"><span class=\"card-cell-label\">기본값</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stream</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span><code>boolean</code></td><td data-cell-label=\"요건\"><span class=\"card-cell-label\">요건</span>선택 사항</td><td data-cell-label=\"값과 한도\"><span class=\"card-cell-label\">값과 한도</span></td><td data-cell-label=\"기본값\" data-default=\"known\"><span class=\"card-cell-label\">기본값</span>false</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>입력 자료 조합</summary><p class=\"note-s\"><b>텍스트</b> · UTF-8 텍스트</p><p class=\"note-s\"><code>messages[].content 문자열</code></p></details><details class=\"note-s\" data-method-contract><summary>메서드 매개변수와 수명 주기</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>매개변수</th><th>명세</th></tr></thead><tbody><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>content_type</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>application/json</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>required</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>model, messages, max_tokens</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>optional_controls</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>stream</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>material_types</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>text</td></tr><tr><th data-cell-label=\"매개변수\" scope=\"row\"><span class=\"card-cell-label\">매개변수</span><code>text_file_material</code></th><td data-cell-label=\"명세\"><span class=\"card-cell-label\">명세</span>실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요.</td></tr></tbody></table></div><p>수명 주기: <code>synchronous_or_streamed</code></p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">요금</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>요금 정보는 요청 옵션을 추가하지 않습니다. 지원되는 매개변수는 선택한 메서드에 표시됩니다.</p><dl data-price-conditions><dt>빠른 모드</dt><dd>표준 요금 <span class=\"note-s\">빠른 모드를 선택한 경우</span></dd><dt>Flex 모드</dt><dd>표준 요금 <span class=\"note-s\">flex 모드를 선택한 경우</span></dd><dt>최대 추론 수준</dt><dd>표준 요금 <span class=\"note-s\">최대 추론 수준에 default 조정값을 적용하는 경우</span></dd><dt>추론 수준 · 높음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 높음인 경우</span></dd><dt>추론 수준 · 낮음</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 낮음인 경우</span></dd><dt>추론 수준 · 최대</dt><dd>표준 요금 <span class=\"note-s\">추론 수준이 최대인 경우</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot 요금</h4><h4>설정별 가격</h4><p class=\"note-s\">각 요금을 표시된 조건과 대조하세요. 서로 대체되는 설정 묶음마다 하나의 요금만 적용하세요.</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>설정</th><th>요금표</th><th>컨텍스트 토큰 수 초과 기준</th><th>컨텍스트 토큰 수 이하 기준</th><th>요금</th></tr></thead><tbody><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>토큰의 기본 단가</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>기본 요금</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr><tr><th data-cell-label=\"설정\" scope=\"row\"><span class=\"card-cell-label\">설정</span>요청 길이 구간 1</th><td data-cell-label=\"요금표\"><span class=\"card-cell-label\">요금표</span>—</td><td data-cell-label=\"컨텍스트 토큰 수 초과 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 초과 기준</span>0</td><td data-cell-label=\"컨텍스트 토큰 수 이하 기준\"><span class=\"card-cell-label\">컨텍스트 토큰 수 이하 기준</span>상한 없음</td><td data-cell-label=\"요금\"><span class=\"card-cell-label\">요금</span><div><span>입력 · 입력 토큰</span> <b>$0.0003</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>출력 · 출력 토큰</span> <b>$0.001</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 읽기</span> <b>$0.00006</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div><div><span>입력 · 캐시 쓰기, 1시간</span> <b>—</b> <span class=\"price-unit\">/ 1K 토큰</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot는 요청 전에 예상 금액을 미리 확보합니다. 결과를 받은 뒤 측정된 사용량을 기준으로 최종 요금을 정산합니다. 스트리밍 정산에는 최종 사용량 기록을 사용합니다. <a href=\"/docs/ko/billing/reserve/\">금액 확보와 정산 방식 →</a></p></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">요청 예제</h3><h4>Ailoot Ultra · Anthropic Messages</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"코드 예제 형식\"><button class=\"cg-tab\" id=\"model-code-721-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-721-panel-0\" aria-selected=\"true\" tabindex=\"0\">최소 구성의 완전한 JSON 본문</button><button class=\"cg-tab\" id=\"model-code-721-tab-1\" role=\"tab\" type=\"button\" aria-controls=\"model-code-721-panel-1\" aria-selected=\"false\" tabindex=\"-1\">curl · 자신의 UTF-8 문서 사용</button><button class=\"cg-tab\" id=\"model-code-721-tab-2\" role=\"tab\" type=\"button\" aria-controls=\"model-code-721-panel-2\" aria-selected=\"false\" tabindex=\"-1\">Python · 결과 전체 저장</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"코드 복사\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-721-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-721-tab-0\"><pre data-lang=\"json\"><code>{\n  &quot;model&quot;: &quot;~z-ai/glm-flash-latest&quot;,\n  &quot;max_tokens&quot;: 128,\n  &quot;messages&quot;: [\n    {\n      &quot;role&quot;: &quot;user&quot;,\n      &quot;content&quot;: &quot;Summarize the incident report.&quot;\n    }\n  ],\n  &quot;stream&quot;: false\n}</code></pre></div><div class=\"cg-pane\" id=\"model-code-721-panel-1\" role=\"tabpanel\" aria-labelledby=\"model-code-721-tab-1\" hidden><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}&quot;\nexport AILOOT_TEXT_FILE\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;~z-ai/glm-flash-latest&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nPath(&#39;request.json&#39;).write_text(json.dumps(payload, ensure_ascii=False), encoding=&#39;utf-8&#39;)\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H &quot;x-api-key: $AILOOT_API_KEY&quot; -H &#39;anthropic-version: 2023-06-01&#39; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - &lt;&lt;&#39;PY_RESULT&#39;\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n</code></pre></div><div class=\"cg-pane\" id=\"model-code-721-panel-2\" role=\"tabpanel\" aria-labelledby=\"model-code-721-tab-2\" hidden><pre data-lang=\"python\"><code>import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ[&#39;AILOOT_TEXT_FILE&#39;])\nif not source_file.is_file():\n    raise SystemExit(&#39;Set AILOOT_TEXT_FILE to your actual UTF-8 document&#39;)\ntext = source_file.read_text(encoding=&#39;utf-8&#39;)\nif not text.strip():\n    raise SystemExit(&#39;Choose a document containing text&#39;)\npayload = {&#39;model&#39;: &#39;~z-ai/glm-flash-latest&#39;, &#39;max_tokens&#39;: 128, &#39;messages&#39;: [{&#39;role&#39;: &#39;user&#39;, &#39;content&#39;: &#39;Summarize the incident report.&#39;}]}\npayload[&#39;messages&#39;][0][&#39;content&#39;] = &#39;Summarize this material and quote supporting source passages.\\n\\n&#39; + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ[&#39;AILOOT_API_KEY&#39;]\nif not api_key.strip():\n    raise SystemExit(&#39;Set AILOOT_API_KEY before making a request&#39;)\nheaders = {&#39;x-api-key&#39;: &#39;PLACEHOLDER_KEY&#39;, &#39;anthropic-version&#39;: &#39;2023-06-01&#39;, &#39;Content-Type&#39;: &#39;application/json&#39;}\nheaders[&#39;x-api-key&#39;] = api_key\nrequest = Request(&#39;https://api.ailoot.ai/v1/messages&#39;, data=json.dumps(payload, ensure_ascii=False).encode(&#39;utf-8&#39;), headers=headers, method=&#39;POST&#39;)\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path(&#39;response-headers.txt&#39;).write_text(str(response.headers), encoding=&#39;utf-8&#39;)\nexcept HTTPError as error:\n    Path(&#39;result.json&#39;).write_bytes(error.read())\n    Path(&#39;response-headers.txt&#39;).write_text(str(error.headers), encoding=&#39;utf-8&#39;)\n    raise\nPath(&#39;result.json&#39;).write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path(&#39;result.json&#39;).read_text(encoding=&#39;utf-8&#39;))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">결과 수신 및 저장</h3><h4>Ailoot Ultra · Anthropic Messages</h4><p class=\"note-s\">JSON 또는 SSE</p><div class=\"card-result-process\" data-all-results><h5>완료된 결과 모두 보관</h5><p class=\"note-s\">반환된 완전한 응답, 파일, 콘텐츠 부분을 모두 보관하세요.</p><p class=\"note-s\">모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>원래 응답을 확인해야 할 경우</h5><p class=\"note-s\">요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다.</p></div><details class=\"card-about\" data-output-fields><summary>응답 필드</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>필드</th><th>유형</th></tr></thead><tbody><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">id</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">content[]</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>text|thinking|tool_use|other content block</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">stop_reason</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>string|null</td></tr><tr><th data-cell-label=\"필드\" scope=\"row\"><span class=\"card-cell-label\">필드</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"유형\" data-field-type><span class=\"card-cell-label\">유형</span>object</td></tr></tbody></table></div></details><details class=\"card-about\" data-method-errors><summary>오류와 다음 단계</summary><div class=\"tw\" data-card-table=\"errors\"><table><thead><tr><th>응답</th><th>조건</th><th>다음 단계</th></tr></thead><tbody><tr><th data-cell-label=\"응답\" scope=\"row\"><span class=\"card-cell-label\">응답</span>400 · <code>invalid_request_error</code></th><td data-cell-label=\"조건\"><span class=\"card-cell-label\">조건</span>필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음</td><td data-cell-label=\"다음 단계\"><span class=\"card-cell-label\">다음 단계</span>새 생성 요청 전에 표시된 필드를 수정하세요.</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">별칭</h3><h4>모델 별칭</h4><p class=\"note-s\"><span data-model-alias-route=\"Core\"><b>Ailoot</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a></span><br><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a></span></p><h4>메서드 경로 별칭</h4><p class=\"note-s\"><code>/chat/completions</code></p><h4>관련 호출용 ID</h4><p class=\"note-s\"><a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=z-ai%2Fglm-5.3-flash&amp;fmt=messages\"><code>z-ai/glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5&amp;fmt=messages\"><code>glm-4.5</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.5-air&amp;fmt=messages\"><code>glm-4.5-air</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.6&amp;fmt=messages\"><code>glm-4.6</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-4.7&amp;fmt=messages\"><code>glm-4.7</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5-turbo&amp;fmt=messages\"><code>glm-5-turbo</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash&amp;fmt=messages\"><code>glm-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-flash-latest&amp;fmt=messages\"><code>glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=~z-ai%2Fglm-flash-latest&amp;fmt=messages\"><code>~z-ai/glm-flash-latest</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Core&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a>, <a href=\"#m=z-ai%2Fglm-5.3-flash&amp;route=Ultra&amp;caller=glm-5.3-flash&amp;fmt=messages\"><code>glm-5.3-flash</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "~z-ai/glm-flash-latest",
        "fmt": "messages",
        "http": "POST",
        "path": "/v1/messages",
        "request_model_id": "~z-ai/glm-flash-latest",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|messages|/v1/messages|~z-ai%2Fglm-flash-latest",
      "ordinal": 31,
      "rawMethod": {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "~z-ai/glm-flash-latest",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 문자열",
                "required_material": "UTF-8 텍스트"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "protocol",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "JSON 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "~z-ai/glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "~z-ai/glm-flash-latest"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "~z-ai/glm-flash-latest",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"~z-ai/glm-flash-latest\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': '~z-ai/glm-flash-latest', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': '~z-ai/glm-flash-latest', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "messages",
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "~z-ai/glm-flash-latest",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    }
  ],
  "model_id": "z-ai/glm-5.3-flash",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "14af784f5c53e177ecfbf878248aedca787b64cad6bbc4757b3e5af820cb5744",
    "input_html_sha256": "d022dfcf7d7ecfcd1c93aae27c36249aa2d7efbfa064a35ee9ab18de9d653748",
    "private_audit_sha256": "223f8352850bad7bd4ce0beaf0aec5eccaa1a5d761360dd4088eaed205935ba9",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/ko/z-ai-glm-5-3-flash/",
    "description": "GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.",
    "locale": "ko",
    "md_url": "https://ailoot.ai/models/ko/z-ai-glm-5-3-flash/index.md",
    "title": "Z.ai: GLM 5.3 Flash — Ailoot",
    "url": "https://ailoot.ai/models/ko/z-ai-glm-5-3-flash/"
  },
  "practicalHtml": "<h3>실제 활용 과제</h3><p>영어 기술 예제</p><pre><code>Audit a report calculation\n\nReview these report rows supplied as text: revenue 12,000; cost of goods 7,000; delivery expense 800; reported gross profit 4,200. The report defines gross profit as revenue minus cost of goods, excluding delivery. Identify the formula mismatch, show the defined calculation and suggest a separate label for the delivery-adjusted figure.</code></pre><h4>예상 결과</h4><pre><code>A formula check, arithmetic using the given definition and a suggested label distinguishing the two measures.</code></pre><h4>결과 확인</h4><pre><code>Check that the report&#x27;s stated definition, rather than an invented accounting rule, determines the correction.</code></pre>",
  "practicalText": "실제 활용 과제 영어 기술 예제 Audit a report calculation Review these report rows supplied as text: revenue 12,000; cost of goods 7,000; delivery expense 800; reported gross profit 4,200. The report defines gross profit as revenue minus cost of goods, excluding delivery. Identify the formula mismatch, show the defined calculation and suggest a separate label for the delivery-adjusted figure. 예상 결과 A formula check, arithmetic using the given definition and a suggested label distinguishing the two measures. 결과 확인 Check that the report's stated definition, rather than an invented accounting rule, determines the correction.",
  "rawModel": {
    "about": "### 작업을 위한 멀티모달 모델\n\nGLM 5.3 Flash는 텍스트, 이미지, 동영상, 파일의 이해를 결합합니다. 텍스트 응답을 생성하며 시각적 피드백을 사용하는 프로그래밍, 문서 처리, 전문 과제를 위해 설계되었습니다. 최대 100만 토큰의 컨텍스트와 12만 8000토큰의 최대 출력이 명시되어 있습니다.\n\n### 긴 컨텍스트의 아키텍처\n\n모델에는 3200억 개의 파라미터가 있으며 180억 개가 활성화됩니다. 하이브리드 어텐션은 희소 처리와 선형 처리를 결합하고, 특별한 층간 연결은 규모가 커질 때 안정성을 유지하는 데 도움이 됩니다. 멀티모달 자료는 사전 학습에 포함되었습니다.\n\n시각 정보는 작업 과정에 참여합니다. 도우미가 인터페이스나 렌더링된 결과를 살펴보고, 과제와 비교하며, 수정을 제안합니다. 개발사가 코드 작성 이후 실제 시각적 결과 검증에 주의를 기울이는 이유입니다.\n\n### 추론, 도구, 데이터\n\n추론은 항상 활성화됩니다. 깊이는 `low`, `high`, `max` 수준으로 선택하며 비활성화 모드는 제공되지 않습니다. 긴 작업에서는 단계 사이의 추론 기록을 유지할 수 있습니다.\n\n도구 작업에서 모델은 함수 이름과 인수를 구성합니다. 애플리케이션이 작업을 실행하고 결과를 반환합니다. JSON은 프로그램으로 응답을 처리하는 데 적합합니다. 기대하는 필드는 지시로 정하고 문법과 값의 의미는 따로 확인합니다. 스트리밍 형식으로 텍스트를 점진적으로 받을 수 있습니다.\n\n반복되는 지시나 기록의 캐싱은 처리된 컨텍스트를 재사용하는 데 도움이 됩니다. Z.ai에 따르면 적절한 과제에서 반복 처리를 줄입니다. 실제 재사용 여부는 개별 요청의 결과로 정해집니다.\n\n### 시각 지시에 따른 개발\n\n모델은 같은 제품의 여러 스크린샷, 페이지 간 관계, 공통 구성 요소, 인터페이스 상태, 애니메이션을 분석할 수 있습니다. 도구가 있는 에이전트 환경에서는 코드를 작성하고, 애플리케이션을 실행하며, 결과의 스크린샷을 살펴보고 불일치를 수정합니다. 게임 개발의 경우 이 과정은 규칙, 움직임, 상호작용, 점수, 게임 세션 종료를 포함합니다.\n\n### 문서와 전문 분석\n\n프레젠테이션, 보고서, 스프레드시트 과제에서는 텍스트, 이미지, 다이어그램, 요소 배치 등 내용과 구성을 함께 고려합니다. 도구를 통해 PPTX, PDF, DOCX, XLSX 자료를 만들고 확인할 수 있습니다. 이런 파일은 애플리케이션 작업의 결과이며 모델의 직접 응답은 텍스트입니다.\n\n재무 분석은 보고서 처리, 수식 일관성 검증, 공개 데이터와 가정 및 결론의 분리 검토를 포함합니다. 개발사가 설명한 과정에서는 지시 자료에서 데이터를 가져옵니다.\n\n### 동영상, 3차원 장면, 인터페이스\n\n에이전트 환경에서 모델은 동영상 자료, 이벤트의 시간 순서, 참여자의 시각적 특징, 자막을 분석할 수 있습니다. 도구는 편집과 결과 저장을 제공합니다.\n\n3차원 장면이나 도면 작업에서는 공간 설명, 비율, 보이는 결과를 연결합니다. 도구 과정에는 구성, 특정 시점에서의 렌더링, 시각 비교, 수정이 포함됩니다. 마찬가지로 애플리케이션 화면을 분석하고 순차적인 인터페이스 작업을 도울 수 있습니다.\n\n이 사례는 필요한 도구가 있는 환경의 모델 특성을 설명합니다. 입력 가능한 자료 구성은 선택한 호출 방식에 따라 정해집니다. 시각적 이해가 모든 요청에서 동영상·파일 처리나 나열된 결과물 생성이 자동 제공된다는 뜻은 아닙니다.",
    "alias_of": null,
    "aliases": [
      "glm-4.5",
      "glm-4.5-air",
      "glm-4.6",
      "glm-4.7",
      "glm-5-turbo",
      "glm-flash",
      "glm-flash-latest",
      "~z-ai/glm-flash-latest",
      "glm-5.3-flash"
    ],
    "author": "Z.ai",
    "available": null,
    "canonical_model": "z-ai/glm-5.3-flash",
    "capabilities": {
      "context_length": 1048576,
      "manufacturer_input": [
        "text",
        "image",
        "video"
      ],
      "manufacturer_output": [
        "text"
      ]
    },
    "card_routes": [
      {
        "label": "Core",
        "rates": [
          {
            "amount": 0.15,
            "amount_unit": "usd_per_million_tokens",
            "key": "in",
            "label": "Input",
            "side": "in"
          },
          {
            "amount": 0.5,
            "amount_unit": "usd_per_million_tokens",
            "key": "out",
            "label": "Output",
            "side": "out"
          }
        ],
        "summary": "구성의 전체 요금 정보는 상세 정보에서 확인할 수 있습니다."
      },
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          }
        ],
        "summary": "구성의 전체 요금 정보는 상세 정보에서 확인할 수 있습니다."
      },
      {
        "label": "Core",
        "rates": [
          {
            "amount": 0.15,
            "amount_unit": "usd_per_million_tokens",
            "key": "in",
            "label": "Input",
            "side": "in"
          },
          {
            "amount": 0.5,
            "amount_unit": "usd_per_million_tokens",
            "key": "out",
            "label": "Output",
            "side": "out"
          }
        ],
        "summary": "구성의 전체 요금 정보는 상세 정보에서 확인할 수 있습니다."
      },
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          }
        ],
        "summary": "구성의 전체 요금 정보는 상세 정보에서 확인할 수 있습니다."
      },
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          }
        ],
        "summary": "구성의 전체 요금 정보는 상세 정보에서 확인할 수 있습니다."
      }
    ],
    "ctx": 1048576,
    "display_name": "Z.ai: GLM 5.3 Flash",
    "entity_type": "model",
    "formats": [
      "messages",
      "responses",
      "chat"
    ],
    "id": "z-ai/glm-5.3-flash",
    "input": [
      "text",
      "image"
    ],
    "kind": "text",
    "max_out": 32768,
    "methods": [
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-5.3-flash\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-5.3-flash\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-5.3-flash',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-5.3-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-5.3-flash\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-5.3-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5.3-flash\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-5.3-flash\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-5.3-flash\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "Send the conversation as text messages. Stream must be a boolean; omitted stream defaults to false."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string",
                "when": "텍스트 대화"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Text conversation at the exact model ID and method path.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "정확한 모델 ID를 messages와 함께 보내세요.",
            "컨텍스트 길이는 출력 상한이 아닙니다.",
            "텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "텍스트 대화. stream은 불리언이며 기본값은 false입니다.",
            "file_material": "실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "role/content 형식의 메시지 배열",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [
            "/chat/completions"
          ],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\":\"glm-5.3-flash\",\"messages\":[{\"role\":\"user\",\"content\":\"hello\"}],\"stream\":false}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model=\"glm-5.3-flash\", messages=[{\"role\":\"user\",\"content\":\"hello\"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [
          "/chat/completions"
        ],
        "out": 1,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Standard rate",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Standard rate",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Standard rate",
            "when": "When maximum reasoning effort uses the default adjustment"
          },
          {
            "label": "Reasoning effort · high",
            "value": "Standard rate",
            "when": "When reasoning effort is high"
          },
          {
            "label": "Reasoning effort · low",
            "value": "Standard rate",
            "when": "When reasoning effort is low"
          },
          {
            "label": "Reasoning effort · max",
            "value": "Standard rate",
            "when": "When reasoning effort is max"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "glm-5.3-flash",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 문자열",
                "required_material": "UTF-8 텍스트"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "protocol",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "JSON 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "glm-5.3-flash"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "glm-5.3-flash",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"glm-5.3-flash\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "messages",
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Standard rate",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Standard rate",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Standard rate",
            "when": "When maximum reasoning effort uses the default adjustment"
          },
          {
            "label": "Reasoning effort · high",
            "value": "Standard rate",
            "when": "When reasoning effort is high"
          },
          {
            "label": "Reasoning effort · low",
            "value": "Standard rate",
            "when": "When reasoning effort is low"
          },
          {
            "label": "Reasoning effort · max",
            "value": "Standard rate",
            "when": "When reasoning effort is max"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.5\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.5\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.5',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.5\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.5\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.5\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.5\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.5\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.5',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5-air"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.5-air\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.5-air\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.5-air',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5-air",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5-air"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.5-air\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.5-air\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.5-air\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5-air",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.5-air"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.5-air\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.5-air\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.5-air\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.5-air',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.5-air",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.6"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.6\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.6\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.6',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.6",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.6"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.6\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.6\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.6\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.6",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.6"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.6\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.6\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.6\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.6',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.6",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.7"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.7\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-4.7\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-4.7\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-4.7',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.7",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.7"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.7\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-4.7\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-4.7\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-4.7\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.7",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-4.7"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-4.7\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-4.7\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-4.7\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-4.7',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-4.7",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5-turbo"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-5-turbo\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-5-turbo\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-5-turbo',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5-turbo",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5-turbo"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-5-turbo\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-5-turbo\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-5-turbo\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5-turbo",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-5-turbo"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-5-turbo\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-5-turbo\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-5-turbo\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-5-turbo',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-5-turbo",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-flash\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-flash\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-flash',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-flash\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-flash\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-flash\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-flash\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image,source:{type:base64,media_type,data}} 또는 type=url인 소스"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"max_tokens\": 1024, \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image\",\"source\":{\"type\":\"base64\",\"media_type\":mime,\"data\":b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"glm-flash-latest\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"glm-flash-latest\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='glm-flash-latest',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "Anthropic Messages",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every output item and content part, actual function call_id, encrypted reasoning and usage. In streaming retain complete event/item identity.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/responses"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "입력 텍스트 또는 input_text 파트",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:input_image,image_url}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 출력 항목과 콘텐츠 파트, 실제 함수 call_id, 암호화된 추론, 사용량을 보존하세요. 스트리밍에서는 이벤트/항목의 식별 정보를 완전하게 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "status",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "output[]",
                  "type": "message|reasoning|function_call|other item"
                },
                {
                  "description": null,
                  "name": "output[].content[]",
                  "type": "content part"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input",
                "required": true,
                "type": "string|input_item[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "message",
                  "reasoning",
                  "function_call",
                  "function_call_output"
                ],
                "enum_known": true,
                "name": "input[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].content",
                "required": false,
                "type": "string|content_part[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].call_id",
                "required": false,
                "type": "string",
                "when": "function_call_output. 실제 반환된 call_id를 유지하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "input[].output",
                "required": false,
                "type": "string|content_part[]",
                "when": "function_call_output"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_output_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning.summary",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "text.verbosity",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "include",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "store",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "identity_rule": "지원되는 이어가기의 실제 응답 ID만 사용",
                "name": "previous_response_id",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_key",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "input"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/responses"
          },
          "operation_modes": [
            "responses"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"input\": \"\"}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"input\"]=\"Summarize this material and quote supporting source passages.\\n\\n\"+text\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"input\": [{\"role\": \"user\", \"content\": [{\"type\": \"input_text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"input\"][0][\"content\"].append({\"type\":\"input_image\",\"image_url\":\"data:\"+mime+\";base64,\"+b64})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(json.loads(Path(\"result.json\").read_text(encoding=\"utf-8\")))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.responses.create(model=\"glm-flash-latest\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\")\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.responses.create({ model: \"glm-flash-latest\", input: \"Explain the difference between an observation and a hypothesis in three sentences.\" });\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "Source_stream_contract": "typed parameters.stream=boolean/source_interface/defaultfalse; outputs.format=json or SSE",
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nwith client.responses.stream(model=\"glm-flash-latest\", input=\"Explain the difference between an observation and a hypothesis in three sentences.\") as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_response()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "creation_argument_parity": "same model/input as existing normal SDK call; SDK sets stream=true",
            "label": "Python streaming · complete Responses result",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "responses",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Responses",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/responses",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": null,
        "cache_write_1h": null,
        "cache_write_5m": null,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              },
              {
                "availability": "Exact model input declaration and selected Source bridge required",
                "file_id_workflow": "No Ailoot upload/file-ID endpoint is introduced by this feed.",
                "mode": "text_plus_image",
                "representation": "{type:image_url,image_url:{url,detail}}"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text",
              "image"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1000000,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}\"\nexport AILOOT_IMAGE_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"glm-flash-latest\", \"messages\": [{\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"Read labels and numbers in this image; flag unreadable text.\"}]}]}')\nimport base64\nf=Path(os.environ[\"AILOOT_IMAGE_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose an actual PNG JPEG or WebP image\")\nraw=f.read_bytes()\nmime=\"image/png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"image/jpeg\" if raw.startswith(b\"\\xff\\xd8\") else \"image/webp\" if raw[:4]==b\"RIFF\" and raw[8:12]==b\"WEBP\" else None\nif not mime:raise SystemExit(\"Use PNG JPEG or WebP\")\nb64=base64.b64encode(raw).decode()\np[\"messages\"][0][\"content\"].append({\"type\":\"image_url\",\"image_url\":{\"url\":\"data:\"+mime+\";base64,\"+b64}})\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use your actual image",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"glm-flash-latest\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"glm-flash-latest\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='glm-flash-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text",
          "image"
        ],
        "label": "OpenAI Chat",
        "max_out": 131072,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "glm-flash-latest",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": 0.15,
        "cache_write_1h": null,
        "cache_write_5m": 0.15,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 또는 type=text 블록",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "system",
                "required": false,
                "type": "string|content_block[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "limit_scope": "선택한 모델/카드의 정확한 상한",
                "minimum": 1,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop_sequences",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "tool[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].name",
                "required": false,
                "type": "string",
                "when": "도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].input_schema",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "thinking.budget_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "output_config.effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "metadata",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "operation_modes": [
            "messages"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 1048576,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"z-ai/glm-5.3-flash\", \"max_tokens\": 1024, \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "import anthropic\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = anthropic.Anthropic(base_url=\"https://api.ailoot.ai\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nmsg = client.messages.create(\n    model=\"z-ai/glm-5.3-flash\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(msg.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import Anthropic from \"@anthropic-ai/sdk\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new Anthropic({ baseURL: \"https://api.ailoot.ai\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst msg = await client.messages.create({\n  model: \"z-ai/glm-5.3-flash\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(msg);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "import anthropic,os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=anthropic.Anthropic(base_url=\"https://api.ailoot.ai\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.messages.stream(model='z-ai/glm-5.3-flash',max_tokens=1024,messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_message()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · complete final message",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "messages",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": 32768,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/messages",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "cache_read": 0.03,
        "cache_write": 0.15,
        "cache_write_1h": null,
        "cache_write_5m": 0.15,
        "conditional_meter": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": []
          },
          "hints": [
            "메서드 형식과 ID는 정확합니다. 공급자의 기능 지원과 요청 수락은 별개입니다."
          ],
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": null,
            "required": [
              "model",
              "messages"
            ],
            "text_file_material": "실제 UTF-8 콘텐츠를 텍스트로 삽입합니다. 파일 ID/URLs에는 별도의 정확한 지원이 필요합니다"
          },
          "lifecycle": {
            "mode": "exact retained published method"
          },
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "operation_modes": [
            "chat_completions"
          ],
          "output": {
            "family": [
              "text"
            ],
            "format": "JSON or supported SSE",
            "multioutputs": "retain every actual response output"
          }
        },
        "ctx": 4096,
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"z-ai/glm-5.3-flash\", \"messages\": []}')\nf=Path(os.environ[\"AILOOT_TEXT_FILE\"])\nif not f.is_file():raise SystemExit(\"Choose your actual UTF-8 source material\")\ntext=f.read_text(encoding=\"utf-8\")\nif not text.strip():raise SystemExit(\"Source material must contain text\")\np[\"messages\"]=[{\"role\":\"user\",\"content\":\"Summarize this material and quote supporting source passages.\\n\\n\"+text}]\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n",
            "label": "Use actual text material",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient = OpenAI(base_url=\"https://api.ailoot.ai/v1\", api_key=os.environ[\"AILOOT_API_KEY\"], max_retries=0)\nresp = client.chat.completions.create(\n    model=\"z-ai/glm-5.3-flash\",\n    messages=[{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}],\n)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(resp.to_dict(mode=\"json\"))\n",
            "label": "Python · retained SDK call",
            "language": "python"
          },
          {
            "SDK_retry_proof": {
              "field": "maxRetries",
              "scope": "normalclient options; no provider/account/proxy switches",
              "source_urls": [
                "https://raw.githubusercontent.com/openai/openai-node/master/src/client.ts",
                "https://raw.githubusercontent.com/anthropics/anthropic-sdk-typescript/main/src/client.ts"
              ],
              "value": 0
            },
            "code": "import OpenAI from \"openai\";\n\nif (!process.env.AILOOT_API_KEY?.trim()) throw new Error(\"Set AILOOT_API_KEY before making a request\");\nconst client = new OpenAI({ baseURL: \"https://api.ailoot.ai/v1\", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });\nconst resp = await client.chat.completions.create({\n  model: \"z-ai/glm-5.3-flash\",\n  messages: [{ role: \"user\", content: \"Explain the difference between an observation and a hypothesis in three sentences.\" }],\n});\nimport { writeFileSync } from \"node:fs\";\n\nfunction saveResult(data, stem = \"result\") {\n  writeFileSync(stem + \".json\", JSON.stringify(data, null, 2));\n  console.log(JSON.stringify(data, null, 2));\n  const saveBlob = (encoded, suffix, label) => {\n    const raw = Buffer.from(encoded, \"base64\");\n    const ext = raw.subarray(0,8).equals(Buffer.from([137,80,78,71,13,10,26,10])) ? \"png\" : raw[0]===255 && raw[1]===216 ? \"jpg\" : raw.subarray(0,4).toString()===\"RIFF\" && raw.subarray(8,12).toString()===\"WEBP\" ? \"webp\" : suffix;\n    const file = `${stem}-${label}.${ext}`;\n    writeFileSync(file, raw); console.log(\"Saved\", file);\n  };\n  for (const [i, block] of (data.content || []).entries()) console.log(\"Content\", i, JSON.stringify(block));\n  for (const choice of data.choices || []) console.log(\"Choice\", choice.index, JSON.stringify(choice.message || choice.delta || {}));\n  for (const [i, item] of (data.output || []).entries()) {\n    console.log(\"Output\", i, JSON.stringify(item));\n    if (item.type === \"image_generation_call\" && item.result) saveBlob(item.result, item.output_format || \"bin\", `output-${i}`);\n  }\n  for (const [ci, candidate] of (data.candidates || []).entries()) {\n    for (const [pi, part] of (candidate.content?.parts || []).entries()) {\n      console.log(\"Candidate/part\", ci, pi, JSON.stringify(part));\n      const blob = part.inlineData || part.inline_data;\n      if (blob?.data) {\n        const mime = blob.mimeType || blob.mime_type;\n        const suffix = ({\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"})[mime] || \"bin\";\n        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);\n      }\n    }\n  }\n}\n\nsaveResult(resp);\n",
            "label": "Node.js · retained SDK call",
            "language": "js"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='z-ai/glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python streaming · retain all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "chat",
        "http": "POST",
        "img_in": null,
        "img_out": null,
        "in": 0.15,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": 1024,
        "max_tool_calls": null,
        "out": 0.5,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "pricing_profiles": [
          {
            "dimensions": {},
            "label": "Core",
            "units": [
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "in",
                "label": "Input",
                "side": "in"
              },
              {
                "amount": 0.5,
                "amount_unit": "usd_per_million_tokens",
                "key": "out",
                "label": "Output",
                "side": "out"
              },
              {
                "amount": 0.03,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_read",
                "label": "Cache read",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write",
                "label": "Cache write",
                "side": "in"
              },
              {
                "amount": 0.15,
                "amount_unit": "usd_per_million_tokens",
                "key": "cache_write_5m",
                "label": "Cache write 5m",
                "side": "in"
              }
            ]
          }
        ],
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Core",
        "status_reads": [],
        "tiers": [],
        "tool_prices": null,
        "unit": "token",
        "units": []
      },
      {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID.",
              "Guarded canonical keys must occur once; duplicate or case-varied model/tools/cap fields are rejected."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": [
                  "function"
                ],
                "enum_known": true,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "text"
                ],
                "enum_known": true,
                "name": "modalities",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "conditions": "이 Ultra 텍스트 경로에서는 provider.options가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "conditions": "실제 프롬프트 캐시 지정 위치에서는 1h가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control.ttl",
                "required": false,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "정확한 모델 ID를 messages와 함께 보내세요.",
            "컨텍스트 길이는 출력 상한이 아닙니다.",
            "텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "모델별로 다름. 사용자 함수 도구와 호스팅 도구는 서로 다릅니다",
            "file_material": "실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "role/content 형식의 메시지 배열",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream",
              "temperature",
              "top_p",
              "stop",
              "max_tokens",
              "max_completion_tokens",
              "reasoning",
              "response_format",
              "tools",
              "tool_choice"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"z-ai/glm-5.3-flash\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model='z-ai/glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='z-ai/glm-5.3-flash',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python SDK streaming · all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "interval_boundary": "min_exclusive_max_inclusive",
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "null_rate_policy": "unknown or inherited; never zero",
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "z-ai/glm-5.3-flash",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 문자열",
                "required_material": "UTF-8 텍스트"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "protocol",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "JSON 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "z-ai/glm-5.3-flash"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "z-ai/glm-5.3-flash"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "z-ai/glm-5.3-flash",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"z-ai/glm-5.3-flash\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'z-ai/glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': 'z-ai/glm-5.3-flash', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "messages",
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.",
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "header": "Authorization: Bearer"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "hints": [
              "Model context is not an output cap.",
              "A model-dependent field needs the exact published model profile; unspecified defaults/enums are not guessed.",
              "Tool calls propose actions; the client application returns actual observations with the returned call ID.",
              "Guarded canonical keys must occur once; duplicate or case-varied model/tools/cap fields are rejected."
            ],
            "ignored_fields": [],
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/chat/completions"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content",
                "required_material": "UTF8 텍스트"
              }
            ],
            "operation_modes": [
              "conversation",
              "function_tool_continuation",
              "streaming"
            ],
            "outputs": {
              "all_results": "각 선택지와 그 콘텐츠·도구 호출·추론을 모두 보존하세요. SSE에서는 선택지/도구 인덱스별로 증분을 조합하고 최종 종료 사유와 사용량을 유지하세요.",
              "family": "text",
              "fields": [
                {
                  "description": null,
                  "name": "choices[].index",
                  "type": "integer"
                },
                {
                  "description": null,
                  "name": "choices[].message.content",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "choices[].message.tool_calls",
                  "type": "tool_call[]"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_content",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "choices[].message.reasoning_details",
                  "type": "object|array"
                },
                {
                  "description": null,
                  "name": "choices[].finish_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "json 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "~z-ai/glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "min_items": 1,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "model_dependent",
                "conditions": "이 역할들은 소스 코드의 호환 타입에 명시적으로 표현됩니다. 정확한 모델 역할 집합은 모델별로 다릅니다.",
                "default": null,
                "default_known": false,
                "enum": [
                  "system",
                  "user",
                  "assistant",
                  "tool",
                  "function"
                ],
                "enum_exhaustive": false,
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": false,
                "type": "string|content_part[]|null"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_calls",
                "required": false,
                "type": "tool_call[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].tool_call_id",
                "required": false,
                "type": "string",
                "when": "role=tool. 실제 반환된 ID를 사용하세요"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].name",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_content",
                "required": false,
                "type": "string",
                "when": "이 모델이 추론을 사용하는 경우 실제 반환된 추론을 그대로 다음 요청에 다시 전달하세요"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].reasoning_details",
                "required": false,
                "type": "object|array"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "minimum": 1,
                "name": "max_completion_tokens",
                "required": false,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stream_options.include_usage",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "top_p",
                "required": false,
                "type": "number"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "stop",
                "required": false,
                "type": "string|string[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools",
                "required": false,
                "type": "function_tool[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": [
                  "function"
                ],
                "enum_known": true,
                "name": "tools[].type",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.name",
                "required": true,
                "type": "string",
                "when": "함수 도구 지정됨"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.description",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tools[].function.parameters",
                "required": false,
                "type": "JSON_schema"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "tool_choice",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "parallel_tool_calls",
                "required": false,
                "type": "boolean"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "response_format",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning_effort",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "reasoning",
                "required": false,
                "type": "object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "service_tier",
                "required": false,
                "type": "string"
              },
              {
                "availability": "source_compatibility",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "instructions",
                "required": false,
                "type": "string"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "functions",
                "required": false,
                "type": "function[]"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "function_call",
                "required": false,
                "type": "string|object"
              },
              {
                "availability": "model_dependent",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "prompt_cache_options",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "text"
                ],
                "enum_known": true,
                "name": "modalities",
                "required": false,
                "type": "string[]"
              },
              {
                "availability": "source_interface",
                "conditions": "이 Ultra 텍스트 경로에서는 provider.options가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "provider",
                "required": false,
                "type": "object"
              },
              {
                "availability": "source_interface",
                "conditions": "실제 프롬프트 캐시 지정 위치에서는 1h가 거부됩니다",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "cache_control.ttl",
                "required": false,
                "type": "string"
              }
            ],
            "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.",
            "unsupported": [
              "additional models/models list",
              "plugins",
              "route",
              "hosted tools; ordinary client function tools remain separate",
              "non-text output modalities",
              "provider.options overrides",
              "one-hour prompt-cache TTL"
            ]
          },
          "hints": [
            "정확한 모델 ID를 messages와 함께 보내세요.",
            "컨텍스트 길이는 출력 상한이 아닙니다.",
            "텍스트 파일은 텍스트를 그대로 제공할 수 있습니다. 이미지/오디오/파일 객체 입력에는 정확한 바인딩이 필요합니다."
          ],
          "input": {
            "content_type": "application/json",
            "control_scope": "모델별로 다름. 사용자 함수 도구와 호스팅 도구는 서로 다릅니다",
            "file_material": "실제 UTF-8 문서를 텍스트로 그대로 삽입합니다. 파일 ID는 추정하지 않습니다",
            "hosted_operations": false,
            "material_types": [
              "text"
            ],
            "messages": "role/content 형식의 메시지 배열",
            "multimodal_input_binding": null,
            "optional_controls": [
              "stream",
              "temperature",
              "top_p",
              "stop",
              "max_tokens",
              "max_completion_tokens",
              "reasoning",
              "response_format",
              "tools",
              "tool_choice"
            ],
            "output_modalities": [
              "text"
            ],
            "required": [
              "model",
              "messages"
            ]
          },
          "lifecycle": {
            "mode": "synchronous_or_streamed",
            "unknown": "preserve original request id; no generic chat job retrieval path"
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/chat/completions"
          },
          "method_aliases": [],
          "operation_modes": [
            "text_chat"
          ],
          "output": {
            "content": "choices[].message.content or stream delta",
            "family": "text",
            "format": "json or supported SSE",
            "tool_calls": "retain actual returned function calls"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{\"model\": \"~z-ai/glm-flash-latest\", \"messages\": [{\"role\": \"user\", \"content\": \"Explain the difference between an observation and a hypothesis in three sentences.\"}]}')\n\nPath(\"request.json\").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path(\"result.json\").read_text())\nfor x in r.get(\"choices\",[]):\n    if x.get(\"message\",{}).get(\"content\"): print(x[\"message\"][\"content\"])\nPY_RESULT\n",
            "label": "curl · retained exact creation",
            "language": "bash"
          },
          {
            "code": "from openai import OpenAI\nimport os\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nresult=client.chat.completions.create(model='~z-ai/glm-flash-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nsave_result(result.to_dict(mode=\"json\"))\n",
            "label": "Python SDK · all choices",
            "language": "python"
          },
          {
            "code": "from openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get(\"AILOOT_API_KEY\", \"\").strip(): raise SystemExit(\"Set AILOOT_API_KEY before making a request\")\nclient=OpenAI(base_url=\"https://api.ailoot.ai/v1\",api_key=os.environ[\"AILOOT_API_KEY\"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem=\"result\"):\n    # Keep every field, including usage, IDs, reasoning and tool requests.\n    Path(stem + \".json\").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding=\"utf-8\")\n    print(json.dumps(data, ensure_ascii=False, indent=2))\n    def save_blob(encoded, suffix, label):\n        raw = base64.b64decode(encoded, altchars=b\"-_\", validate=True)\n        ext = \"png\" if raw.startswith(b\"\\x89PNG\\r\\n\\x1a\\n\") else \"jpg\" if raw.startswith(b\"\\xff\\xd8\") else \"webp\" if raw[:4] == b\"RIFF\" and raw[8:12] == b\"WEBP\" else suffix\n        file = Path(stem + \"-\" + label + \".\" + ext)\n        file.write_bytes(raw)\n        print(\"Saved\", file)\n    for index, block in enumerate(data.get(\"content\") or []):\n        print(\"Content\", index, json.dumps(block, ensure_ascii=False))\n    for choice in data.get(\"choices\") or []:\n        print(\"Choice\", choice.get(\"index\"), json.dumps(choice.get(\"message\", choice.get(\"delta\", {})), ensure_ascii=False))\n    for index, item in enumerate(data.get(\"output\") or []):\n        print(\"Output\", index, json.dumps(item, ensure_ascii=False))\n        if item.get(\"type\") == \"image_generation_call\" and item.get(\"result\"):\n            save_blob(item[\"result\"], item.get(\"output_format\") or \"bin\", \"output-\" + str(index))\n    for ci, candidate in enumerate(data.get(\"candidates\") or []):\n        for pi, part in enumerate((candidate.get(\"content\") or {}).get(\"parts\") or []):\n            print(\"Candidate/part\", ci, pi, json.dumps(part, ensure_ascii=False))\n            blob = part.get(\"inlineData\") or part.get(\"inline_data\")\n            if blob and blob.get(\"data\"):\n                mime = blob.get(\"mimeType\") or blob.get(\"mime_type\")\n                suffix = {\"image/png\":\"png\", \"image/jpeg\":\"jpg\", \"image/webp\":\"webp\", \"audio/wav\":\"wav\", \"audio/mpeg\":\"mp3\", \"video/mp4\":\"mp4\"}.get(mime, \"bin\")\n                save_blob(blob[\"data\"], suffix, \"candidate-\" + str(ci) + \"-part-\" + str(pi))\n\nwith client.chat.completions.stream(model='~z-ai/glm-flash-latest',messages=[{\"role\":\"user\",\"content\":\"Explain observations and hypotheses in three sentences.\"}]) as stream:\n    with Path(\"stream-events.jsonl\").open(\"w\",encoding=\"utf-8\") as log:\n        for event in stream:\n            payload=event.to_dict(mode=\"json\")\n            log.write(json.dumps(payload,ensure_ascii=False)+\"\\n\"); log.flush()\n            print(json.dumps(payload,ensure_ascii=False))\n    final=stream.get_final_completion()\n    save_result(final.to_dict(mode=\"json\"),\"stream-result\")\n",
            "label": "Python SDK streaming · all events",
            "language": "python"
          }
        ],
        "family": "openai",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "chat",
        "hints": [
          "Send exact model ID with messages.",
          "Context length is not an output cap.",
          "A text file may supply literal text; image/audio/file-object inputs need exact binding."
        ],
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "OpenAI Chat",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "text"
        ],
        "path": "/v1/chat/completions",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "~z-ai/glm-flash-latest",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "interval_boundary": "min_exclusive_max_inclusive",
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "null_rate_policy": "unknown or inherited; never zero",
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "available": null,
        "cache_read": 0.06,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "authentication": {
              "api_key_source": "AILOOT_API_KEY",
              "headers": [
                "Authorization: Bearer",
                "x-api-key",
                "anthropic-version"
              ],
              "version_example": "2023-06-01"
            },
            "errors": [
              {
                "code": null,
                "condition": "필수 필드, 자료 표현 방식 또는 파라미터 값이 올바르지 않음",
                "http_status": 400,
                "recovery": "새 생성 요청 전에 표시된 필드를 수정하세요.",
                "type": "invalid_request_error"
              }
            ],
            "example_body": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "~z-ai/glm-flash-latest",
              "stream": false
            },
            "lifecycle": {
              "create": {
                "http": "POST",
                "path": "/v1/messages"
              },
              "job_read": null,
              "mode": "synchronous_or_streamed",
              "unknown": "요청/응답 ID와 헤더를 보존하세요. 텍스트 작업을 조회하는 범용 URL은 제공되지 않습니다."
            },
            "material_combinations": [
              {
                "mode": "text",
                "representation": "messages[].content 문자열",
                "required_material": "UTF-8 텍스트"
              }
            ],
            "operation_modes": [
              "synchronous_json",
              "streamed_SSE"
            ],
            "outputs": {
              "all_results": "모든 콘텐츠 블록, 사고 서명, 실제 도구 사용 ID를 보존하세요. 모든 SSE 블록 증분을 조합하세요. 첫 텍스트 블록이 전체 출력은 아닙니다.",
              "family": "protocol",
              "fields": [
                {
                  "description": null,
                  "name": "id",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "model",
                  "type": "string"
                },
                {
                  "description": null,
                  "name": "content[]",
                  "type": "text|thinking|tool_use|other content block"
                },
                {
                  "description": null,
                  "name": "stop_reason",
                  "type": "string|null"
                },
                {
                  "description": null,
                  "name": "usage",
                  "type": "object"
                }
              ],
              "format": "JSON 또는 SSE"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "~z-ai/glm-flash-latest"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages",
                "required": true,
                "type": "message[]"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": [
                  "user",
                  "assistant"
                ],
                "enum_known": true,
                "name": "messages[].role",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "messages[].content",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "default": null,
                "default_known": false,
                "enum": null,
                "enum_known": false,
                "name": "max_tokens",
                "required": true,
                "type": "integer"
              },
              {
                "availability": "source_interface",
                "default": false,
                "default_known": true,
                "enum": null,
                "enum_known": false,
                "name": "stream",
                "required": false,
                "type": "boolean"
              }
            ],
            "profile_binding": "Documented current stock Messages bridge; optional model capabilities are separate from this minimal text request.",
            "request_schema": {
              "additionalProperties": false,
              "properties": {
                "max_tokens": {
                  "minimum": 1,
                  "type": "integer"
                },
                "messages": {
                  "items": {
                    "additionalProperties": false,
                    "properties": {
                      "content": {
                        "oneOf": [
                          {
                            "type": "string"
                          },
                          {
                            "items": {
                              "oneOf": [
                                {
                                  "properties": {
                                    "text": {
                                      "type": "string"
                                    },
                                    "type": {
                                      "const": "text"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "text"
                                  ],
                                  "type": "object"
                                },
                                {
                                  "properties": {
                                    "source": {
                                      "oneOf": [
                                        {
                                          "properties": {
                                            "type": {
                                              "const": "url"
                                            },
                                            "url": {
                                              "type": "string"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "url"
                                          ],
                                          "type": "object"
                                        },
                                        {
                                          "properties": {
                                            "data": {
                                              "type": "string"
                                            },
                                            "media_type": {
                                              "type": "string"
                                            },
                                            "type": {
                                              "const": "base64"
                                            }
                                          },
                                          "required": [
                                            "type",
                                            "media_type",
                                            "data"
                                          ],
                                          "type": "object"
                                        }
                                      ]
                                    },
                                    "type": {
                                      "const": "image"
                                    }
                                  },
                                  "required": [
                                    "type",
                                    "source"
                                  ],
                                  "type": "object"
                                }
                              ]
                            },
                            "type": "array"
                          }
                        ]
                      },
                      "role": {
                        "enum": [
                          "user",
                          "assistant"
                        ],
                        "type": "string"
                      }
                    },
                    "required": [
                      "role",
                      "content"
                    ],
                    "type": "object"
                  },
                  "minItems": 1,
                  "type": "array"
                },
                "model": {
                  "enum": [
                    "~z-ai/glm-flash-latest"
                  ],
                  "type": "string"
                },
                "stream": {
                  "default": false,
                  "type": "boolean"
                }
              },
              "required": [
                "model",
                "messages",
                "max_tokens"
              ],
              "type": "object"
            },
            "schema_template": {
              "max_tokens": 128,
              "messages": [
                {
                  "content": "Summarize the incident report.",
                  "role": "user"
                }
              ],
              "model": "~z-ai/glm-flash-latest",
              "stream": false
            },
            "unsupported": [
              "No query API key.",
              "Hosted/server-side tools and model-specific optional controls are not part of this minimal family example."
            ]
          },
          "input": {
            "content_type": "application/json",
            "material_types": [
              "text"
            ],
            "optional_controls": [
              "stream"
            ],
            "required": [
              "model",
              "messages",
              "max_tokens"
            ],
            "text_file_material": "실제 UTF-8 문서를 읽고 그 텍스트를 지정된 입력 또는 메시지 콘텐츠 문자열에 넣으세요."
          },
          "lifecycle": {
            "create": {
              "http": "POST",
              "path": "/v1/messages"
            },
            "job_read": null,
            "mode": "synchronous_or_streamed",
            "unknown": "Keep request/response IDs and headers. No generic text job retrieval URL is supplied."
          },
          "manufacturer_capability": null,
          "method": {
            "http": "POST",
            "path": "/v1/messages"
          },
          "output": {
            "all_results": "Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.",
            "family": "protocol",
            "format": "JSON or SSE"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "토큰의 기본 단가",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "요청 길이 구간 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "{\n  \"model\": \"~z-ai/glm-flash-latest\",\n  \"max_tokens\": 128,\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"Summarize the incident report.\"\n    }\n  ],\n  \"stream\": false\n}",
            "label": "Complete minimal JSON body",
            "language": "json"
          },
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}\"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': '~z-ai/glm-flash-latest', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n  -H \"x-api-key: $AILOOT_API_KEY\" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\n",
            "label": "curl · use your UTF-8 document",
            "language": "bash"
          },
          {
            "code": "import json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n    raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n    raise SystemExit('Choose a document containing text')\npayload = {'model': '~z-ai/glm-flash-latest', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n    raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n    with urlopen(request, timeout=120) as response:\n        raw = response.read()\n        Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n    Path('result.json').write_bytes(error.read())\n    Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n    raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\n",
            "label": "Python · save the complete result",
            "language": "python"
          }
        ],
        "family": "anthropic",
        "fast_multiplier": 1,
        "flex_multiplier": 1,
        "fmt": "messages",
        "http": "POST",
        "in": 0.3,
        "input": [
          "text"
        ],
        "label": "Anthropic Messages",
        "max_out": null,
        "max_reasoning_effort_multiplier": 1,
        "method_aliases": [],
        "out": 1,
        "output": [
          "json",
          "sse"
        ],
        "path": "/v1/messages",
        "price_conditions": [
          {
            "label": "빠른 모드",
            "value": "표준 요금",
            "when": "빠른 모드를 선택한 경우"
          },
          {
            "label": "Flex 모드",
            "value": "표준 요금",
            "when": "flex 모드를 선택한 경우"
          },
          {
            "label": "최대 추론 수준",
            "value": "표준 요금",
            "when": "최대 추론 수준에 default 조정값을 적용하는 경우"
          },
          {
            "label": "추론 수준 · 높음",
            "value": "표준 요금",
            "when": "추론 수준이 높음인 경우"
          },
          {
            "label": "추론 수준 · 낮음",
            "value": "표준 요금",
            "when": "추론 수준이 낮음인 경우"
          },
          {
            "label": "추론 수준 · 최대",
            "value": "표준 요금",
            "when": "추론 수준이 최대인 경우"
          }
        ],
        "pricing": {
          "billing_mode": "token",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "max_context_tokens_inclusive": null,
              "min_context_tokens_exclusive": 0
            },
            "label": "Request-length tier 1",
            "units": [
              {
                "amount": "0.0003000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": "0.0000003",
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": "0.001000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": "0.000001",
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": "0.00006000",
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": "0.00000006",
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          }
        ],
        "reasoning_effort_multipliers": {
          "high": 1,
          "low": 1,
          "max": 1
        },
        "request_model_id": "~z-ai/glm-flash-latest",
        "route_label": "Ultra",
        "status_reads": [],
        "tiers": [
          {
            "cache_read": 0.06,
            "cache_read_multiplier": null,
            "cache_write": null,
            "cache_write_1h": null,
            "cache_write_multiplier": null,
            "created_at": "0001-01-01T00:00:00Z",
            "in": 0.3,
            "input_multiplier": null,
            "max": null,
            "max_tokens": null,
            "min": 0,
            "min_tokens": 0,
            "out": 1,
            "output_multiplier": null,
            "per_request_price": null,
            "sort_order": 0,
            "tier_label": "",
            "updated_at": "0001-01-01T00:00:00Z"
          }
        ],
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-5.3-flash",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-5.3-flash",
        "route_label": "Ultra"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-4.5",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-4.5-air",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-4.6",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-4.7",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-5-turbo",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-flash",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "glm-flash-latest",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Core"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "z-ai/glm-5.3-flash",
        "route_label": "Ultra"
      },
      {
        "canonical_model_id": "z-ai/glm-5.3-flash",
        "request_model_id": "~z-ai/glm-flash-latest",
        "route_label": "Ultra"
      }
    ],
    "name": "z-ai/glm-5.3-flash",
    "price": {
      "in": 0.15,
      "in_label": null,
      "out": 0.5,
      "out_label": null,
      "scope_label": "Token rates",
      "sort_in": 0.15,
      "sort_out": 0.5,
      "varies": true
    },
    "pricing_profiles": [
      {
        "dimensions": {
          "regime": "base"
        },
        "label": "OpenAI Chat · 기본 토큰 요금",
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "dimensions": {
          "max_context_tokens_inclusive": null,
          "min_context_tokens_exclusive": 0
        },
        "label": "OpenAI Chat · 요청 길이 구간 1",
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "dimensions": {
          "regime": "base"
        },
        "label": "Anthropic Messages · 기본 토큰 요금",
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      },
      {
        "dimensions": {
          "max_context_tokens_inclusive": null,
          "min_context_tokens_exclusive": 0
        },
        "label": "Anthropic Messages · 요청 길이 구간 1",
        "units": [
          {
            "amount": "0.0003000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": "0.0000003",
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": "0.001000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": "0.000001",
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": "0.00006000",
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": "0.00000006",
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          }
        ]
      }
    ],
    "public_id": "z-ai/glm-5.3-flash",
    "short": "GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다."
  },
  "renderer_schema": {
    "method_order": "Original DTO methods order; every exact route/format/path/caller survives.",
    "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers."
  },
  "representation": "exact-public-dto-and-native-renderer-html",
  "representationNotes": {
    "current_reference": {
      "about_json_pointer": "/aboutHtml",
      "methods": [
        {
          "contract_json_pointer": "/methods/0/rawMethod/contract",
          "html_json_pointer": "/methods/0/html",
          "method_ordinal": 0
        },
        {
          "contract_json_pointer": "/methods/1/rawMethod/contract",
          "html_json_pointer": "/methods/1/html",
          "method_ordinal": 1
        },
        {
          "contract_json_pointer": "/methods/2/rawMethod/contract",
          "html_json_pointer": "/methods/2/html",
          "method_ordinal": 2
        },
        {
          "contract_json_pointer": "/methods/3/rawMethod/contract",
          "html_json_pointer": "/methods/3/html",
          "method_ordinal": 3
        },
        {
          "contract_json_pointer": "/methods/4/rawMethod/contract",
          "html_json_pointer": "/methods/4/html",
          "method_ordinal": 4
        },
        {
          "contract_json_pointer": "/methods/5/rawMethod/contract",
          "html_json_pointer": "/methods/5/html",
          "method_ordinal": 5
        },
        {
          "contract_json_pointer": "/methods/6/rawMethod/contract",
          "html_json_pointer": "/methods/6/html",
          "method_ordinal": 6
        },
        {
          "contract_json_pointer": "/methods/7/rawMethod/contract",
          "html_json_pointer": "/methods/7/html",
          "method_ordinal": 7
        },
        {
          "contract_json_pointer": "/methods/8/rawMethod/contract",
          "html_json_pointer": "/methods/8/html",
          "method_ordinal": 8
        },
        {
          "contract_json_pointer": "/methods/9/rawMethod/contract",
          "html_json_pointer": "/methods/9/html",
          "method_ordinal": 9
        },
        {
          "contract_json_pointer": "/methods/10/rawMethod/contract",
          "html_json_pointer": "/methods/10/html",
          "method_ordinal": 10
        },
        {
          "contract_json_pointer": "/methods/11/rawMethod/contract",
          "html_json_pointer": "/methods/11/html",
          "method_ordinal": 11
        },
        {
          "contract_json_pointer": "/methods/12/rawMethod/contract",
          "html_json_pointer": "/methods/12/html",
          "method_ordinal": 12
        },
        {
          "contract_json_pointer": "/methods/13/rawMethod/contract",
          "html_json_pointer": "/methods/13/html",
          "method_ordinal": 13
        },
        {
          "contract_json_pointer": "/methods/14/rawMethod/contract",
          "html_json_pointer": "/methods/14/html",
          "method_ordinal": 14
        },
        {
          "contract_json_pointer": "/methods/15/rawMethod/contract",
          "html_json_pointer": "/methods/15/html",
          "method_ordinal": 15
        },
        {
          "contract_json_pointer": "/methods/16/rawMethod/contract",
          "html_json_pointer": "/methods/16/html",
          "method_ordinal": 16
        },
        {
          "contract_json_pointer": "/methods/17/rawMethod/contract",
          "html_json_pointer": "/methods/17/html",
          "method_ordinal": 17
        },
        {
          "contract_json_pointer": "/methods/18/rawMethod/contract",
          "html_json_pointer": "/methods/18/html",
          "method_ordinal": 18
        },
        {
          "contract_json_pointer": "/methods/19/rawMethod/contract",
          "html_json_pointer": "/methods/19/html",
          "method_ordinal": 19
        },
        {
          "contract_json_pointer": "/methods/20/rawMethod/contract",
          "html_json_pointer": "/methods/20/html",
          "method_ordinal": 20
        },
        {
          "contract_json_pointer": "/methods/21/rawMethod/contract",
          "html_json_pointer": "/methods/21/html",
          "method_ordinal": 21
        },
        {
          "contract_json_pointer": "/methods/22/rawMethod/contract",
          "html_json_pointer": "/methods/22/html",
          "method_ordinal": 22
        },
        {
          "contract_json_pointer": "/methods/23/rawMethod/contract",
          "html_json_pointer": "/methods/23/html",
          "method_ordinal": 23
        },
        {
          "contract_json_pointer": "/methods/24/rawMethod/contract",
          "html_json_pointer": "/methods/24/html",
          "method_ordinal": 24
        },
        {
          "contract_json_pointer": "/methods/25/rawMethod/contract",
          "html_json_pointer": "/methods/25/html",
          "method_ordinal": 25
        },
        {
          "contract_json_pointer": "/methods/26/rawMethod/contract",
          "html_json_pointer": "/methods/26/html",
          "method_ordinal": 26
        },
        {
          "contract_json_pointer": "/methods/27/rawMethod/contract",
          "html_json_pointer": "/methods/27/html",
          "method_ordinal": 27
        },
        {
          "contract_json_pointer": "/methods/28/rawMethod/contract",
          "html_json_pointer": "/methods/28/html",
          "method_ordinal": 28
        },
        {
          "contract_json_pointer": "/methods/29/rawMethod/contract",
          "html_json_pointer": "/methods/29/html",
          "method_ordinal": 29
        },
        {
          "contract_json_pointer": "/methods/30/rawMethod/contract",
          "html_json_pointer": "/methods/30/html",
          "method_ordinal": 30
        },
        {
          "contract_json_pointer": "/methods/31/rawMethod/contract",
          "html_json_pointer": "/methods/31/html",
          "method_ordinal": 31
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod",
        "/methods/1/rawMethod",
        "/methods/2/rawMethod",
        "/methods/3/rawMethod",
        "/methods/4/rawMethod",
        "/methods/5/rawMethod",
        "/methods/6/rawMethod",
        "/methods/7/rawMethod",
        "/methods/8/rawMethod",
        "/methods/9/rawMethod",
        "/methods/10/rawMethod",
        "/methods/11/rawMethod",
        "/methods/12/rawMethod",
        "/methods/13/rawMethod",
        "/methods/14/rawMethod",
        "/methods/15/rawMethod",
        "/methods/16/rawMethod",
        "/methods/17/rawMethod",
        "/methods/18/rawMethod",
        "/methods/19/rawMethod",
        "/methods/20/rawMethod",
        "/methods/21/rawMethod",
        "/methods/22/rawMethod",
        "/methods/23/rawMethod",
        "/methods/24/rawMethod",
        "/methods/25/rawMethod",
        "/methods/26/rawMethod",
        "/methods/27/rawMethod",
        "/methods/28/rawMethod",
        "/methods/29/rawMethod",
        "/methods/30/rawMethod",
        "/methods/31/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "GLM 5.3 Flash는 시각적 개발, 문서 분석, 텍스트 결과를 반환하는 에이전트 작업을 위한 Z.ai 멀티모달 모델입니다.",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "6b057a33c1c8dee77541ad8b52394c6daf7b29718b571f1027f7b94e6862cd88",
    "renderer_sha256": "6825a317438b70ab0939441dcebefece462384e77f7e96cce899605c4b208caa"
  },
  "sourceRevision": "5afdabb58684ff29e7bdbc0e086451ca0be792be72b46501bf44e53bb4850f6e"
}
