模型
控制台

MoonshotAI: Kimi K3 (256K)

Markdown · JSON

k3-256k

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

關於模型

此說明介紹模型的能力。Ailoot 可用的輸入、輸出與選項，依所選方法列於下方。

固定視窗大小的 K3

k3-256k 是 Kimi K3 的版本，上下文為 262 144 個 token。它保留 K3 的用途：長時間工程任務、程式碼與工具工作，以及視覺資料分析。這個版本的視窗固定，因此需求、專案資料與工作歷史，必須納入同一個共用容量。

程式碼與視覺回饋

模型用於循序開發，包括閱讀儲存庫、修改程式碼，以及利用執行結果。廠商將 K3 用於計算程式碼最佳化、編譯器建立與大型專案。視覺資料可協助連結實作與螢幕上可見的成果。

k3-256k 已確認接受影像輸入。這份模型說明接受文字與影像，模型回傳文字。終端機、檔案讀取與程式執行工具，必須由應用程式接入，其結果可用於延續對話。

研究工作

K3 將文獻與資料分析連結到程式開發。透過工具，它可參與計算實作、公式驗證及互動分析資料準備，適合需要將結論與計算連結，並呈現其取得過程的任務。

推理與架構

模型支援 low、high 與 max；廠商目前設定中，high 是 k3-256k 的預設值。使用工具時，模型運用先前回覆與推理的歷史。

K3 架構共有 2.8 兆個參數，處理時啟用約 104B。長上下文使用 Kimi Delta Attention 與 Attention Residuals，視覺輸入使用 MoonViT-V2。這份模型說明代表的正是 262 144 個 token 視窗版本。

長時間工作階段的限制

K3 對推理歷史的完整性敏感。廠商提醒，若未完整傳送歷史，或在另一個模型的工作途中改用 K3，回覆可能不穩定。在複雜任務中，它也可能過度主動，在目標不明確時自行選擇動作。因此，工具工作需要明確指定允許的動作與停止條件。

實用任務

實用任務

英文技術範例

Preserve evaluation order in a compiler rewrite

A compiler optimizer replaces f() * 0 with 0. In this language, function calls may log messages or raise errors, and left-to-right evaluation is observable. Explain why the rewrite is unsafe, give the condition under which it would be valid and propose two regression tests. Return a focused optimization rule rather than a whole compiler design.

預期結果

A concise diagnosis, a guarded rewrite rule and two tests covering observable effects.

檢查結果

The rule does not discard a call unless its lack of observable effects is established.
Ailoot · Anthropic Messages POST /v1/messages k3-256k

k3-256k

Moonshot /k3-256k
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · Anthropic Messages POST /v1/messages
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
k3-256k
預設值—
欄位messages類型message[]要求必填值與限制
項目數下限: 1
預設值—
欄位messages[].role類型string要求必填值與限制
user, assistant
預設值—
欄位messages[].content類型string|content_block[]要求必填值與限制預設值—
欄位system類型string|content_block[]要求選填值與限制預設值—
欄位max_tokens類型integer要求必填值與限制
最小值: 1
限制適用對象: 所選模型／卡片的確切上限
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位stop_sequences類型string[]要求選填值與限制
依模型而定
預設值—
欄位tools類型tool[]要求選填值與限制
依模型而定
預設值—
欄位tools[].name類型string要求選填值與限制
適用條件: 已提供工具
預設值—
欄位tools[].description類型string要求選填值與限制預設值—
欄位tools[].input_schema類型JSON_schema要求選填值與限制預設值—
欄位tool_choice類型object要求選填值與限制
依模型而定
預設值—
欄位thinking.type類型string要求選填值與限制
依模型而定
預設值—
欄位thinking.budget_tokens類型integer要求選填值與限制
依模型而定
預設值—
欄位output_config.effort類型string要求選填值與限制
依模型而定
預設值—
欄位metadata類型object要求選填值與限制預設值—
欄位cache_control類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

messages[].content 或 type=text 區塊

文字 + 圖片

{type:image,source:{type:base64,media_type,data}} 或 type=url 的來源

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, messages, max_tokens
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot Anthropic MessagesPOST /v1/messages
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · Anthropic Messages

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="k3-256k",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))

import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "k3-256k",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);

import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='k3-256k',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · Anthropic Messages

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留所有內容區塊、思考簽章與實際工具使用 ID。組合所有 SSE 區塊增量；第一個文字區塊不是完整輸出。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位id類型string
欄位model類型string
欄位content[]類型text|thinking|tool_use|other content block
欄位stop_reason類型string|null
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · OpenAI Responses POST /v1/responses k3-256k

k3-256k

Moonshot /k3-256k
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · OpenAI Responses POST /v1/responses
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
k3-256k
預設值—
欄位input類型string|input_item[]要求必填值與限制預設值—
欄位instructions類型string要求選填值與限制預設值—
欄位input[].type類型string要求選填值與限制
message, reasoning, function_call, function_call_output
預設值—
欄位input[].content類型string|content_part[]要求選填值與限制預設值—
欄位input[].call_id類型string要求選填值與限制
適用條件: function_call_output；保留實際回傳的 call_id
預設值—
欄位input[].output類型string|content_part[]要求選填值與限制
適用條件: function_call_output
預設值—
欄位max_output_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位tools類型tool[]要求選填值與限制
依模型而定
預設值—
欄位tool_choice類型string|object要求選填值與限制
依模型而定
預設值—
欄位parallel_tool_calls類型boolean要求選填值與限制
依模型而定
預設值—
欄位reasoning.effort類型string要求選填值與限制
依模型而定
預設值—
欄位reasoning.summary類型string要求選填值與限制
依模型而定
預設值—
欄位text.format類型object要求選填值與限制
依模型而定
預設值—
欄位text.verbosity類型string要求選填值與限制
依模型而定
預設值—
欄位include類型string[]要求選填值與限制
依模型而定
預設值—
欄位store類型boolean要求選填值與限制
依模型而定
預設值—
欄位previous_response_id類型string要求選填值與限制
ID 要求: 僅限支援的延續流程實際回傳的回應 ID
依模型而定
預設值—
欄位service_tier類型string要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_key類型string要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_options類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

輸入文字或 input_text 部分

文字 + 圖片

{type:input_image,image_url}

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, input
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot OpenAI ResponsesPOST /v1/responses
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · OpenAI Responses

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT

from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="k3-256k", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))

import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "k3-256k", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);

from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="k3-256k", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · OpenAI Responses

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留每個輸出項目與內容部分、實際函式 call_id、加密推理與用量。串流時保留完整事件／項目身分。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位id類型string
欄位status類型string
欄位output[]類型message|reasoning|function_call|other item
欄位output[].content[]類型content part
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · OpenAI Chat POST /v1/chat/completions k3-256k

k3-256k

Moonshot /k3-256k
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · OpenAI Chat POST /v1/chat/completions
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
k3-256k
預設值—
欄位messages類型message[]要求必填值與限制
項目數下限: 1
預設值—
欄位messages[].role類型string要求必填值與限制
範例：system, user, assistant, tool, function
條件: 這些角色由 原始碼中的相容型別明確表示；確切角色集合仍依模型而定。
依模型而定
預設值—
欄位messages[].content類型string|content_part[]|null要求選填值與限制預設值—
欄位messages[].tool_calls類型tool_call[]要求選填值與限制預設值—
欄位messages[].tool_call_id類型string要求選填值與限制
適用條件: role=tool；使用實際回傳的 ID
預設值—
欄位messages[].name類型string要求選填值與限制預設值—
欄位messages[].reasoning_content類型string要求選填值與限制
適用條件: 此模型使用推理內容時，將實際回傳的推理內容帶回後續請求
預設值—
欄位messages[].reasoning_details類型object|array要求選填值與限制
依模型而定
預設值—
欄位max_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位max_completion_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位stream_options.include_usage類型boolean要求選填值與限制
依模型而定
預設值—
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位stop類型string|string[]要求選填值與限制
依模型而定
預設值—
欄位tools類型function_tool[]要求選填值與限制
依模型而定
預設值—
欄位tools[].type類型string要求選填值與限制
依模型而定
預設值—
欄位tools[].function.name類型string要求必填值與限制
適用條件: 已提供函式工具
預設值—
欄位tools[].function.description類型string要求選填值與限制預設值—
欄位tools[].function.parameters類型JSON_schema要求選填值與限制預設值—
欄位tool_choice類型string|object要求選填值與限制
依模型而定
預設值—
欄位parallel_tool_calls類型boolean要求選填值與限制
依模型而定
預設值—
欄位response_format類型object要求選填值與限制
依模型而定
預設值—
欄位reasoning_effort類型string要求選填值與限制
依模型而定
預設值—
欄位reasoning類型object要求選填值與限制
依模型而定
預設值—
欄位service_tier類型string要求選填值與限制
依模型而定
預設值—
欄位instructions類型string要求選填值與限制
相容性欄位
預設值—
欄位functions類型function[]要求選填值與限制
依模型而定
預設值—
欄位function_call類型string|object要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_options類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

messages[].content

文字 + 圖片

{type:image_url,image_url:{url,detail}}

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, messages
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot OpenAI ChatPOST /v1/chat/completions
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · OpenAI Chat

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "k3-256k", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="k3-256k",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))

import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "k3-256k",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);

from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='k3-256k',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · OpenAI Chat

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留每個候選項及其內容／工具呼叫／推理。SSE 中依候選項／工具索引組合增量，保留最終完成原因與用量。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位choices[].index類型integer
欄位choices[].message.content類型string|null
欄位choices[].message.tool_calls類型tool_call[]
欄位choices[].message.reasoning_content類型string
欄位choices[].message.reasoning_details類型object|array
欄位choices[].finish_reason類型string|null
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · Anthropic Messages POST /v1/messages kimi-256k

kimi-256k

Moonshot /kimi-256k
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · Anthropic Messages POST /v1/messages
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
kimi-256k
預設值—
欄位messages類型message[]要求必填值與限制
項目數下限: 1
預設值—
欄位messages[].role類型string要求必填值與限制
user, assistant
預設值—
欄位messages[].content類型string|content_block[]要求必填值與限制預設值—
欄位system類型string|content_block[]要求選填值與限制預設值—
欄位max_tokens類型integer要求必填值與限制
最小值: 1
限制適用對象: 所選模型／卡片的確切上限
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位stop_sequences類型string[]要求選填值與限制
依模型而定
預設值—
欄位tools類型tool[]要求選填值與限制
依模型而定
預設值—
欄位tools[].name類型string要求選填值與限制
適用條件: 已提供工具
預設值—
欄位tools[].description類型string要求選填值與限制預設值—
欄位tools[].input_schema類型JSON_schema要求選填值與限制預設值—
欄位tool_choice類型object要求選填值與限制
依模型而定
預設值—
欄位thinking.type類型string要求選填值與限制
依模型而定
預設值—
欄位thinking.budget_tokens類型integer要求選填值與限制
依模型而定
預設值—
欄位output_config.effort類型string要求選填值與限制
依模型而定
預設值—
欄位metadata類型object要求選填值與限制預設值—
欄位cache_control類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

messages[].content 或 type=text 區塊

文字 + 圖片

{type:image,source:{type:base64,media_type,data}} 或 type=url 的來源

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, messages, max_tokens
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot Anthropic MessagesPOST /v1/messages
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · Anthropic Messages

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="kimi-256k",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))

import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "kimi-256k",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);

import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='kimi-256k',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · Anthropic Messages

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留所有內容區塊、思考簽章與實際工具使用 ID。組合所有 SSE 區塊增量；第一個文字區塊不是完整輸出。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位id類型string
欄位model類型string
欄位content[]類型text|thinking|tool_use|other content block
欄位stop_reason類型string|null
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · OpenAI Responses POST /v1/responses kimi-256k

kimi-256k

Moonshot /kimi-256k
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · OpenAI Responses POST /v1/responses
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
kimi-256k
預設值—
欄位input類型string|input_item[]要求必填值與限制預設值—
欄位instructions類型string要求選填值與限制預設值—
欄位input[].type類型string要求選填值與限制
message, reasoning, function_call, function_call_output
預設值—
欄位input[].content類型string|content_part[]要求選填值與限制預設值—
欄位input[].call_id類型string要求選填值與限制
適用條件: function_call_output；保留實際回傳的 call_id
預設值—
欄位input[].output類型string|content_part[]要求選填值與限制
適用條件: function_call_output
預設值—
欄位max_output_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位tools類型tool[]要求選填值與限制
依模型而定
預設值—
欄位tool_choice類型string|object要求選填值與限制
依模型而定
預設值—
欄位parallel_tool_calls類型boolean要求選填值與限制
依模型而定
預設值—
欄位reasoning.effort類型string要求選填值與限制
依模型而定
預設值—
欄位reasoning.summary類型string要求選填值與限制
依模型而定
預設值—
欄位text.format類型object要求選填值與限制
依模型而定
預設值—
欄位text.verbosity類型string要求選填值與限制
依模型而定
預設值—
欄位include類型string[]要求選填值與限制
依模型而定
預設值—
欄位store類型boolean要求選填值與限制
依模型而定
預設值—
欄位previous_response_id類型string要求選填值與限制
ID 要求: 僅限支援的延續流程實際回傳的回應 ID
依模型而定
預設值—
欄位service_tier類型string要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_key類型string要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_options類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

輸入文字或 input_text 部分

文字 + 圖片

{type:input_image,image_url}

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, input
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot OpenAI ResponsesPOST /v1/responses
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · OpenAI Responses

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT

from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="kimi-256k", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))

import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "kimi-256k", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);

from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="kimi-256k", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · OpenAI Responses

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留每個輸出項目與內容部分、實際函式 call_id、加密推理與用量。串流時保留完整事件／項目身分。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位id類型string
欄位status類型string
欄位output[]類型message|reasoning|function_call|other item
欄位output[].content[]類型content part
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · OpenAI Chat POST /v1/chat/completions kimi-256k

kimi-256k

Moonshot /kimi-256k
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · OpenAI Chat POST /v1/chat/completions
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
kimi-256k
預設值—
欄位messages類型message[]要求必填值與限制
項目數下限: 1
預設值—
欄位messages[].role類型string要求必填值與限制
範例：system, user, assistant, tool, function
條件: 這些角色由 原始碼中的相容型別明確表示；確切角色集合仍依模型而定。
依模型而定
預設值—
欄位messages[].content類型string|content_part[]|null要求選填值與限制預設值—
欄位messages[].tool_calls類型tool_call[]要求選填值與限制預設值—
欄位messages[].tool_call_id類型string要求選填值與限制
適用條件: role=tool；使用實際回傳的 ID
預設值—
欄位messages[].name類型string要求選填值與限制預設值—
欄位messages[].reasoning_content類型string要求選填值與限制
適用條件: 此模型使用推理內容時，將實際回傳的推理內容帶回後續請求
預設值—
欄位messages[].reasoning_details類型object|array要求選填值與限制
依模型而定
預設值—
欄位max_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位max_completion_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位stream_options.include_usage類型boolean要求選填值與限制
依模型而定
預設值—
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位stop類型string|string[]要求選填值與限制
依模型而定
預設值—
欄位tools類型function_tool[]要求選填值與限制
依模型而定
預設值—
欄位tools[].type類型string要求選填值與限制
依模型而定
預設值—
欄位tools[].function.name類型string要求必填值與限制
適用條件: 已提供函式工具
預設值—
欄位tools[].function.description類型string要求選填值與限制預設值—
欄位tools[].function.parameters類型JSON_schema要求選填值與限制預設值—
欄位tool_choice類型string|object要求選填值與限制
依模型而定
預設值—
欄位parallel_tool_calls類型boolean要求選填值與限制
依模型而定
預設值—
欄位response_format類型object要求選填值與限制
依模型而定
預設值—
欄位reasoning_effort類型string要求選填值與限制
依模型而定
預設值—
欄位reasoning類型object要求選填值與限制
依模型而定
預設值—
欄位service_tier類型string要求選填值與限制
依模型而定
預設值—
欄位instructions類型string要求選填值與限制
相容性欄位
預設值—
欄位functions類型function[]要求選填值與限制
依模型而定
預設值—
欄位function_call類型string|object要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_options類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

messages[].content

文字 + 圖片

{type:image_url,image_url:{url,detail}}

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, messages
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot OpenAI ChatPOST /v1/chat/completions
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · OpenAI Chat

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="kimi-256k",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))

import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "kimi-256k",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);

from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='kimi-256k',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · OpenAI Chat

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留每個候選項及其內容／工具呼叫／推理。SSE 中依候選項／工具索引組合增量，保留最終完成原因與用量。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位choices[].index類型integer
欄位choices[].message.content類型string|null
欄位choices[].message.tool_calls類型tool_call[]
欄位choices[].message.reasoning_content類型string
欄位choices[].message.reasoning_details類型object|array
欄位choices[].finish_reason類型string|null
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · Anthropic Messages POST /v1/messages kimi-256k-latest

kimi-256k-latest

Moonshot /kimi-256k-latest
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · Anthropic Messages POST /v1/messages
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
kimi-256k-latest
預設值—
欄位messages類型message[]要求必填值與限制
項目數下限: 1
預設值—
欄位messages[].role類型string要求必填值與限制
user, assistant
預設值—
欄位messages[].content類型string|content_block[]要求必填值與限制預設值—
欄位system類型string|content_block[]要求選填值與限制預設值—
欄位max_tokens類型integer要求必填值與限制
最小值: 1
限制適用對象: 所選模型／卡片的確切上限
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位stop_sequences類型string[]要求選填值與限制
依模型而定
預設值—
欄位tools類型tool[]要求選填值與限制
依模型而定
預設值—
欄位tools[].name類型string要求選填值與限制
適用條件: 已提供工具
預設值—
欄位tools[].description類型string要求選填值與限制預設值—
欄位tools[].input_schema類型JSON_schema要求選填值與限制預設值—
欄位tool_choice類型object要求選填值與限制
依模型而定
預設值—
欄位thinking.type類型string要求選填值與限制
依模型而定
預設值—
欄位thinking.budget_tokens類型integer要求選填值與限制
依模型而定
預設值—
欄位output_config.effort類型string要求選填值與限制
依模型而定
預設值—
欄位metadata類型object要求選填值與限制預設值—
欄位cache_control類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

messages[].content 或 type=text 區塊

文字 + 圖片

{type:image,source:{type:base64,media_type,data}} 或 type=url 的來源

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, messages, max_tokens
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot Anthropic MessagesPOST /v1/messages
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · Anthropic Messages

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "max_tokens": 1024, "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "max_tokens": 1024, "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image","source":{"type":"base64","media_type":mime,"data":b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
  -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

import anthropic
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = anthropic.Anthropic(base_url="https://api.ailoot.ai", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
msg = client.messages.create(
    model="kimi-256k-latest",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(msg.to_dict(mode="json"))

import Anthropic from "@anthropic-ai/sdk";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new Anthropic({ baseURL: "https://api.ailoot.ai", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const msg = await client.messages.create({
  model: "kimi-256k-latest",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(msg);

import anthropic,os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=anthropic.Anthropic(base_url="https://api.ailoot.ai",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.messages.stream(model='kimi-256k-latest',max_tokens=1024,messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_message()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · Anthropic Messages

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留所有內容區塊、思考簽章與實際工具使用 ID。組合所有 SSE 區塊增量；第一個文字區塊不是完整輸出。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位id類型string
欄位model類型string
欄位content[]類型text|thinking|tool_use|other content block
欄位stop_reason類型string|null
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · OpenAI Responses POST /v1/responses kimi-256k-latest

kimi-256k-latest

Moonshot /kimi-256k-latest
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · OpenAI Responses POST /v1/responses
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
kimi-256k-latest
預設值—
欄位input類型string|input_item[]要求必填值與限制預設值—
欄位instructions類型string要求選填值與限制預設值—
欄位input[].type類型string要求選填值與限制
message, reasoning, function_call, function_call_output
預設值—
欄位input[].content類型string|content_part[]要求選填值與限制預設值—
欄位input[].call_id類型string要求選填值與限制
適用條件: function_call_output；保留實際回傳的 call_id
預設值—
欄位input[].output類型string|content_part[]要求選填值與限制
適用條件: function_call_output
預設值—
欄位max_output_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位tools類型tool[]要求選填值與限制
依模型而定
預設值—
欄位tool_choice類型string|object要求選填值與限制
依模型而定
預設值—
欄位parallel_tool_calls類型boolean要求選填值與限制
依模型而定
預設值—
欄位reasoning.effort類型string要求選填值與限制
依模型而定
預設值—
欄位reasoning.summary類型string要求選填值與限制
依模型而定
預設值—
欄位text.format類型object要求選填值與限制
依模型而定
預設值—
欄位text.verbosity類型string要求選填值與限制
依模型而定
預設值—
欄位include類型string[]要求選填值與限制
依模型而定
預設值—
欄位store類型boolean要求選填值與限制
依模型而定
預設值—
欄位previous_response_id類型string要求選填值與限制
ID 要求: 僅限支援的延續流程實際回傳的回應 ID
依模型而定
預設值—
欄位service_tier類型string要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_key類型string要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_options類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

輸入文字或 input_text 部分

文字 + 圖片

{type:input_image,image_url}

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, input
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot OpenAI ResponsesPOST /v1/responses
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · OpenAI Responses

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "input": ""}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["input"]="Summarize this material and quote supporting source passages.\n\n"+text
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "input": [{"role": "user", "content": [{"type": "input_text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["input"][0]["content"].append({"type":"input_image","image_url":"data:"+mime+";base64,"+b64})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/responses \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(json.loads(Path("result.json").read_text(encoding="utf-8")))
PY_RESULT

from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.responses.create(model="kimi-256k-latest", input="Explain the difference between an observation and a hypothesis in three sentences.")
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))

import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.responses.create({ model: "kimi-256k-latest", input: "Explain the difference between an observation and a hypothesis in three sentences." });
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);

from openai import OpenAI
import os
from pathlib import Path
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
with client.responses.stream(model="kimi-256k-latest", input="Explain the difference between an observation and a hypothesis in three sentences.") as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_response()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · OpenAI Responses

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留每個輸出項目與內容部分、實際函式 call_id、加密推理與用量。串流時保留完整事件／項目身分。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位id類型string
欄位status類型string
欄位output[]類型message|reasoning|function_call|other item
欄位output[].content[]類型content part
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

Ailoot · OpenAI Chat POST /v1/chat/completions kimi-256k-latest

kimi-256k-latest

Moonshot /kimi-256k-latest
模型 ID
  • k3-256k
  • kimi-256k
  • kimi-256k-latest

入門

Kimi K3 的版本，上下文為 262 144 個 token，用於開發及文字、影像分析。

接受的輸入
文字 · 圖片
結果
文字

Ailoot 可用 · 輸入與方法

Ailoot · OpenAI Chat POST /v1/chat/completions
輸入
text, image
輸出
text
上下文
262,144 tokens
輸出上限
65,536 tokens
輸出格式
json 或 SSE
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
kimi-256k-latest
預設值—
欄位messages類型message[]要求必填值與限制
項目數下限: 1
預設值—
欄位messages[].role類型string要求必填值與限制
範例：system, user, assistant, tool, function
條件: 這些角色由 原始碼中的相容型別明確表示；確切角色集合仍依模型而定。
依模型而定
預設值—
欄位messages[].content類型string|content_part[]|null要求選填值與限制預設值—
欄位messages[].tool_calls類型tool_call[]要求選填值與限制預設值—
欄位messages[].tool_call_id類型string要求選填值與限制
適用條件: role=tool；使用實際回傳的 ID
預設值—
欄位messages[].name類型string要求選填值與限制預設值—
欄位messages[].reasoning_content類型string要求選填值與限制
適用條件: 此模型使用推理內容時，將實際回傳的推理內容帶回後續請求
預設值—
欄位messages[].reasoning_details類型object|array要求選填值與限制
依模型而定
預設值—
欄位max_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位max_completion_tokens類型integer要求選填值與限制
最小值: 1
依模型而定
預設值—
欄位stream類型boolean要求選填值與限制預設值false
欄位stream_options.include_usage類型boolean要求選填值與限制
依模型而定
預設值—
欄位temperature類型number要求選填值與限制
依模型而定
預設值—
欄位top_p類型number要求選填值與限制
依模型而定
預設值—
欄位stop類型string|string[]要求選填值與限制
依模型而定
預設值—
欄位tools類型function_tool[]要求選填值與限制
依模型而定
預設值—
欄位tools[].type類型string要求選填值與限制
依模型而定
預設值—
欄位tools[].function.name類型string要求必填值與限制
適用條件: 已提供函式工具
預設值—
欄位tools[].function.description類型string要求選填值與限制預設值—
欄位tools[].function.parameters類型JSON_schema要求選填值與限制預設值—
欄位tool_choice類型string|object要求選填值與限制
依模型而定
預設值—
欄位parallel_tool_calls類型boolean要求選填值與限制
依模型而定
預設值—
欄位response_format類型object要求選填值與限制
依模型而定
預設值—
欄位reasoning_effort類型string要求選填值與限制
依模型而定
預設值—
欄位reasoning類型object要求選填值與限制
依模型而定
預設值—
欄位service_tier類型string要求選填值與限制
依模型而定
預設值—
欄位instructions類型string要求選填值與限制
相容性欄位
預設值—
欄位functions類型function[]要求選填值與限制
依模型而定
預設值—
欄位function_call類型string|object要求選填值與限制
依模型而定
預設值—
欄位prompt_cache_options類型object要求選填值與限制
依模型而定
預設值—
輸入素材組合

文字 · UTF8 文字

messages[].content

文字 + 圖片

{type:image_url,image_url:{url,detail}}

方法參數與生命週期
參數規格
參數material_types規格text, image
參數required規格model, messages
參數optional_controls規格null
參數content_type規格application/json
參數text_file_material規格實際 UTF-8 內容以文字插入；檔案 ID／URLs 需要另有精確支援

生命週期： exact retained published method

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot OpenAI ChatPOST /v1/chat/completions
輸入
US$0.003 / 1K
輸出
US$0.015 / 1K
讀取快取
US$0.0003 / 1K
寫入快取
US$0.003 / 1K
寫入快取，5 分鐘
US$0.003 / 1K tokens

Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。預留金額與結算的運作方式 →

請求範例

Ailoot · OpenAI Chat

文字範例輸入，圖片Python SDKNode.js SDKPython 串流
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 source-material file}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "messages": []}')
f=Path(os.environ["AILOOT_TEXT_FILE"])
if not f.is_file():raise SystemExit("Choose your actual UTF-8 source material")
text=f.read_text(encoding="utf-8")
if not text.strip():raise SystemExit("Source material must contain text")
p["messages"]=[{"role":"user","content":"Summarize this material and quote supporting source passages.\n\n"+text}]
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_IMAGE_FILE:?Set your actual PNG JPEG or WebP image}"
export AILOOT_IMAGE_FILE
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model": "kimi-256k-latest", "messages": [{"role": "user", "content": [{"type": "text", "text": "Read labels and numbers in this image; flag unreadable text."}]}]}')
import base64
f=Path(os.environ["AILOOT_IMAGE_FILE"])
if not f.is_file():raise SystemExit("Choose an actual PNG JPEG or WebP image")
raw=f.read_bytes()
mime="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
if not mime:raise SystemExit("Use PNG JPEG or WebP")
b64=base64.b64encode(raw).decode()
p["messages"][0]["content"].append({"type":"image_url","image_url":{"url":"data:"+mime+";base64,"+b64}})
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
print(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))
PY_RESULT

from openai import OpenAI
import os

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client = OpenAI(base_url="https://api.ailoot.ai/v1", api_key=os.environ["AILOOT_API_KEY"], max_retries=0)
resp = client.chat.completions.create(
    model="kimi-256k-latest",
    messages=[{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}],
)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

save_result(resp.to_dict(mode="json"))

import OpenAI from "openai";

if (!process.env.AILOOT_API_KEY?.trim()) throw new Error("Set AILOOT_API_KEY before making a request");
const client = new OpenAI({ baseURL: "https://api.ailoot.ai/v1", apiKey: process.env.AILOOT_API_KEY, maxRetries: 0 });
const resp = await client.chat.completions.create({
  model: "kimi-256k-latest",
  messages: [{ role: "user", content: "Explain the difference between an observation and a hypothesis in three sentences." }],
});
import { writeFileSync } from "node:fs";

function saveResult(data, stem = "result") {
  writeFileSync(stem + ".json", JSON.stringify(data, null, 2));
  console.log(JSON.stringify(data, null, 2));
  const saveBlob = (encoded, suffix, label) => {
    const raw = Buffer.from(encoded, "base64");
    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;
    const file = `${stem}-${label}.${ext}`;
    writeFileSync(file, raw); console.log("Saved", file);
  };
  for (const [i, block] of (data.content || []).entries()) console.log("Content", i, JSON.stringify(block));
  for (const choice of data.choices || []) console.log("Choice", choice.index, JSON.stringify(choice.message || choice.delta || {}));
  for (const [i, item] of (data.output || []).entries()) {
    console.log("Output", i, JSON.stringify(item));
    if (item.type === "image_generation_call" && item.result) saveBlob(item.result, item.output_format || "bin", `output-${i}`);
  }
  for (const [ci, candidate] of (data.candidates || []).entries()) {
    for (const [pi, part] of (candidate.content?.parts || []).entries()) {
      console.log("Candidate/part", ci, pi, JSON.stringify(part));
      const blob = part.inlineData || part.inline_data;
      if (blob?.data) {
        const mime = blob.mimeType || blob.mime_type;
        const suffix = ({"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"})[mime] || "bin";
        saveBlob(blob.data, suffix, `candidate-${ci}-part-${pi}`);
      }
    }
  }
}

saveResult(resp);

from openai import OpenAI
import os
from pathlib import Path

if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
import base64, json
from pathlib import Path

def save_result(data, stem="result"):
    # Keep every field, including usage, IDs, reasoning and tool requests.
    Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
    print(json.dumps(data, ensure_ascii=False, indent=2))
    def save_blob(encoded, suffix, label):
        raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
        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
        file = Path(stem + "-" + label + "." + ext)
        file.write_bytes(raw)
        print("Saved", file)
    for index, block in enumerate(data.get("content") or []):
        print("Content", index, json.dumps(block, ensure_ascii=False))
    for choice in data.get("choices") or []:
        print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
    for index, item in enumerate(data.get("output") or []):
        print("Output", index, json.dumps(item, ensure_ascii=False))
        if item.get("type") == "image_generation_call" and item.get("result"):
            save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
    for ci, candidate in enumerate(data.get("candidates") or []):
        for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
            print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
            blob = part.get("inlineData") or part.get("inline_data")
            if blob and blob.get("data"):
                mime = blob.get("mimeType") or blob.get("mime_type")
                suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
                save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))

with client.chat.completions.stream(model='kimi-256k-latest',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:
    with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:
        for event in stream:
            payload=event.to_dict(mode="json")
            log.write(json.dumps(payload,ensure_ascii=False)+"\n"); log.flush()
            print(json.dumps(payload,ensure_ascii=False))
    final=stream.get_final_completion()
    save_result(final.to_dict(mode="json"),"stream-result")

接收並儲存結果

Ailoot · OpenAI Chat

json 或 SSE

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留每個候選項及其內容／工具呼叫／推理。SSE 中依候選項／工具索引組合增量，保留最終完成原因與用量。

需要檢查原始回應時

保留請求／回應 ID 與標頭。未提供通用的文字工作擷取 URL。

回應欄位
欄位類型
欄位choices[].index類型integer
欄位choices[].message.content類型string|null
欄位choices[].message.tool_calls類型tool_call[]
欄位choices[].message.reasoning_content類型string
欄位choices[].message.reasoning_details類型object|array
欄位choices[].finish_reason類型string|null
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。

別名

模型別名

Ailoot k3-256k, kimi-256k, kimi-256k-latest

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

k3-256k, kimi-256k, kimi-256k-latest

FAQ · MoonshotAI: Kimi K3 (256K)
可以使用哪些輸入與結果？

POST /v1/messages · k3-256k: text, image → text

POST /v1/responses · k3-256k: text, image → text

POST /v1/chat/completions · k3-256k: text, image → text

POST /v1/messages · kimi-256k: text, image → text

POST /v1/responses · kimi-256k: text, image → text

POST /v1/chat/completions · kimi-256k: text, image → text

POST /v1/messages · kimi-256k-latest: text, image → text

POST /v1/responses · kimi-256k-latest: text, image → text

POST /v1/chat/completions · kimi-256k-latest: text, image → text

請求使用哪些欄位？

POST /v1/messages · k3-256k: model, messages, system, max_tokens, stream, metadata

POST /v1/responses · k3-256k: model, input, instructions, stream

POST /v1/chat/completions · k3-256k: model, messages, stream

POST /v1/messages · kimi-256k: model, messages, system, max_tokens, stream, metadata

POST /v1/responses · kimi-256k: model, input, instructions, stream

POST /v1/chat/completions · kimi-256k: model, messages, stream

POST /v1/messages · kimi-256k-latest: model, messages, system, max_tokens, stream, metadata

POST /v1/responses · kimi-256k-latest: model, input, instructions, stream

POST /v1/chat/completions · kimi-256k-latest: model, messages, stream

適用哪些限制？

POST /v1/messages · k3-256k: ctx: 262144; max_out: 65536; messages.min_items: 1; max_tokens.minimum: 1

POST /v1/responses · k3-256k: ctx: 262144; max_out: 65536

POST /v1/chat/completions · k3-256k: ctx: 262144; max_out: 65536; messages.min_items: 1

POST /v1/messages · kimi-256k: ctx: 262144; max_out: 65536; messages.min_items: 1; max_tokens.minimum: 1

POST /v1/responses · kimi-256k: ctx: 262144; max_out: 65536

POST /v1/chat/completions · kimi-256k: ctx: 262144; max_out: 65536; messages.min_items: 1

POST /v1/messages · kimi-256k-latest: ctx: 262144; max_out: 65536; messages.min_items: 1; max_tokens.minimum: 1

POST /v1/responses · kimi-256k-latest: ctx: 262144; max_out: 65536

POST /v1/chat/completions · kimi-256k-latest: ctx: 262144; max_out: 65536; messages.min_items: 1

更多詳情

將 Ailoot 串接 Claude Code、OpenCode、Hermes 或自己的應用程式。

公司及其專案組合

公司及其專案組合：數百萬客戶，每月銷售額達數十億。

優惠購買 token。

訂閱優惠適合持續工作，折扣碼購買 token 最高可折 50%。

訂閱
為定期請求選擇優惠方案。
最高 50% 折扣碼
購買時輸入代碼，價格依活動重算。
歷史中的費用
每次請求保存模型、token 與金額。

選擇訂閱 · 查看模型價格

將 API 加入 你銷售的產品。

依 Ailoot 正式服務條款與授權合約串接 SaaS、應用程式與機器人；轉售請申請經銷授權。

商用應用程式
在付費功能加入文字、圖片、影片與聲音生成。
經銷授權
提供專案說明與存取方式，要求書面使用和轉售條件。
網站文件
串接前可閱讀正式服務條款、授權合約與資料處理政策。

申請經銷授權 · 正式服務條款與授權合約

登入註冊控制台
方案
入門
連線設定
API
控制台 API
整合
帳務
說明