claude-haiku-4-5-20251001
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- Ailoot · Anthropic Messages
POST /v1/messagesclaude-haiku-4-5-20251001 - Ailoot · OpenAI Responses
POST /v1/responsesclaude-haiku-4-5-20251001 - Ailoot · OpenAI Chat
POST /v1/chat/completionsclaude-haiku-4-5-20251001 - Ailoot · Anthropic Messages
POST /v1/messagesclaude-haiku - Ailoot · OpenAI Responses
POST /v1/responsesclaude-haiku - Ailoot · OpenAI Chat
POST /v1/chat/completionsclaude-haiku - Ailoot · Anthropic Messages
POST /v1/messagesclaude-haiku-latest - Ailoot · OpenAI Responses
POST /v1/responsesclaude-haiku-latest - Ailoot · OpenAI Chat
POST /v1/chat/completionsclaude-haiku-latest
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。
每一步的回應都重要時
Anthropic 為對話助理、使用者服務、協作程式碼工作及原型開發設計了 Claude Haiku 4.5。適合使用者提問、取得結果後,立即調整下一步的循環。Anthropic 表示,此版本的回應延遲較低;實際時間取決於任務與應用程式。
Haiku 4.5 也適用於大量獨立任務。代理流程可將特定子任務交給它,再把結果傳給系統其他部分。描述的用途包括程式設計、推理及介面操作。應用程式提供對應工具時,模型才可呼叫工具或控制電腦;單次文字請求不會讓它取得工作環境的存取權。
一般回應與手動推理預算
包含多個邏輯步驟的任務可使用 extended thinking:應用程式明確啟用推理,並透過 budget_tokens 設定預算。方法支援這些設定時,手動 budget_tokens 預算須至少為 1024 個 Token,且小於 max_tokens,以保留最終回應空間。前者引導分析量,max_tokens 則限制所有輸出。Haiku 4.5 使用的是手動模式;此版本不支援自適應推理或透過 effort 控制深度,也不支援在連續工具呼叫之間進行推理。
選擇任務時,應考量這項差異。一般模式適合直接對話;啟用推理則讓模型有空間分析程式碼或複雜問題。任務內容仍決定須分析哪些資訊,以及以何種形式呈現結果。
素材與版本限制
模型接受文字與圖片,以文字回傳結果。脈絡視窗為200 千個 Token,回應上限為64 千個 Token。圖片與問題共同作為分析素材:模型可說明可見內容,並將其連結到文字任務。支援圖片輸入不代表能建立或編輯圖片。
模型開發商的一般視覺輸入格式為 JPEG/PNG/GIF/WebP,動畫使用第一個影格。原生分析時,長邊為 1568 像素,使用 1568 個視覺 Token;較大圖片會在分析前縮小。檔案與參數支援取決於應用程式的方法。
Anthropic 將此版本的交談風格描述為精簡、直接。宜事先指定所需詳細程度、結果形式及任務限制。可靠的內建知識界線為二月 2025 年;較晚事件的資訊須包含在任務素材中,或透過應用程式可用的工具取得。部分請求可能遭到拒絕。
若方法提供取樣設定,不能同時設定 temperature 與 top_p:此版本只能選擇其中一項。
實用任務
實用任務
英文技術範例
Answer a delivery question
Write a concise support reply using only these notes: order R17 left the warehouse Tuesday; the carrier estimates Friday delivery; the customer asks if Thursday is guaranteed. Explain the current estimate, answer the guarantee question directly and offer to check a new carrier update if one becomes available. Keep the reply under 80 words.預期結果
A customer-ready reply under 80 words, preserving the order ID and delivery estimate.檢查結果
Check that the reply never guarantees Thursday or invents a tracking update.Ailoot · Anthropic Messages POST /v1/messages claude-haiku-4-5-20251001
claude-haiku-4-5-20251001claude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku-4-5-20251001 | 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
POST /v1/messages- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · Anthropic Messages
set -eu
: "${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": "claude-haiku-4-5-20251001", "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": "claude-haiku-4-5-20251001", "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="claude-haiku-4-5-20251001",
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: "claude-haiku-4-5-20251001",
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='claude-haiku-4-5-20251001',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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · OpenAI Responses POST /v1/responses claude-haiku-4-5-20251001
claude-haiku-4-5-20251001claude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku-4-5-20251001 | 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
POST /v1/responses- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · OpenAI Responses
set -eu
: "${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": "claude-haiku-4-5-20251001", "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": "claude-haiku-4-5-20251001", "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="claude-haiku-4-5-20251001", 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: "claude-haiku-4-5-20251001", 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="claude-haiku-4-5-20251001", 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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · OpenAI Chat POST /v1/chat/completions claude-haiku-4-5-20251001
claude-haiku-4-5-20251001claude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku-4-5-20251001 | 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
POST /v1/chat/completions- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · OpenAI Chat
set -eu
: "${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": "claude-haiku-4-5-20251001", "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": "claude-haiku-4-5-20251001", "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="claude-haiku-4-5-20251001",
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: "claude-haiku-4-5-20251001",
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='claude-haiku-4-5-20251001',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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · Anthropic Messages POST /v1/messages claude-haiku
claude-haikuclaude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku | 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
POST /v1/messages- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · Anthropic Messages
set -eu
: "${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": "claude-haiku", "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": "claude-haiku", "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="claude-haiku",
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: "claude-haiku",
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='claude-haiku',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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · OpenAI Responses POST /v1/responses claude-haiku
claude-haikuclaude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku | 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
POST /v1/responses- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · OpenAI Responses
set -eu
: "${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": "claude-haiku", "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": "claude-haiku", "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="claude-haiku", 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: "claude-haiku", 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="claude-haiku", 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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · OpenAI Chat POST /v1/chat/completions claude-haiku
claude-haikuclaude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku | 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
POST /v1/chat/completions- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · OpenAI Chat
set -eu
: "${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": "claude-haiku", "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": "claude-haiku", "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="claude-haiku",
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: "claude-haiku",
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='claude-haiku',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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · Anthropic Messages POST /v1/messages claude-haiku-latest
claude-haiku-latestclaude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku-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
POST /v1/messages- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · Anthropic Messages
set -eu
: "${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": "claude-haiku-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": "claude-haiku-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="claude-haiku-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: "claude-haiku-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='claude-haiku-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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · OpenAI Responses POST /v1/responses claude-haiku-latest
claude-haiku-latestclaude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku-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
POST /v1/responses- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · OpenAI Responses
set -eu
: "${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": "claude-haiku-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": "claude-haiku-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="claude-haiku-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: "claude-haiku-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="claude-haiku-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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
Ailoot · OpenAI Chat POST /v1/chat/completions claude-haiku-latest
claude-haiku-latestclaude-haiku-4-5-20251001claude-haikuclaude-haiku-latest
入門
Claude Haiku 4.5 用於互動式助理、使用者支援、日常資訊處理及程式碼工作。複雜問題可使用獨立的推理模式。
- 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
- 200,000 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 claude-haiku-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
POST /v1/chat/completions- 輸入
- US$0.001 / 1K
- 輸出
- US$0.005 / 1K
- 讀取快取
- US$0.0001 / 1K
- 寫入快取
- US$0.00125 / 1K
- 寫入快取,5 分鐘
- US$0.00125 / 1K tokens
- 寫入快取,1 小時
- US$0.002 / 1K tokens
- web_search_call
- US$0.01 每次呼叫
- 最大呼叫次數 web_search_call
- 8
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 →
參考費率詳情
模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。
anthropic/claude-haiku-4.5
各設定的價格
| 設定 | 計費條件 | 費用 |
|---|---|---|
| 設定anthropic/claude-haiku-4.5 · 預設設定 | 計費條件預設設定 | 費用 輸入 · 輸入 US$0.002 / 1K Token 輸出 · 輸出 US$0.01 / 1K Token |
claude-haiku-4-5-20251001 · 公布價格
各設定的價格
| 設定 | 費用 |
|---|---|
| 設定claude-haiku-4-5-20251001 · 公布價格 | 費用 輸入 · 寫入快取 $0.0025 每 1K Token 輸入 · 讀取快取 $0.0002 每 1K Token 輸入 · 輸入 Token $0.002 每 1K Token 輸出 · 輸出 Token $0.010 每 1K Token 每次請求 $0.000 每次請求 |
請求範例
Ailoot · OpenAI Chat
set -eu
: "${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": "claude-haiku-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": "claude-haiku-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="claude-haiku-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: "claude-haiku-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='claude-haiku-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 claude-haiku-4-5-20251001, claude-haiku, claude-haiku-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
claude-haiku-4-5-20251001, claude-haiku, claude-haiku-latest
FAQ · claude-haiku-4-5-20251001
- 可以使用哪些輸入與結果?
POST /v1/messages·claude-haiku-4-5-20251001:text,image→textPOST /v1/responses·claude-haiku-4-5-20251001:text,image→textPOST /v1/chat/completions·claude-haiku-4-5-20251001:text,image→textPOST /v1/messages·claude-haiku:text,image→textPOST /v1/responses·claude-haiku:text,image→textPOST /v1/chat/completions·claude-haiku:text,image→textPOST /v1/messages·claude-haiku-latest:text,image→textPOST /v1/responses·claude-haiku-latest:text,image→textPOST /v1/chat/completions·claude-haiku-latest:text,image→text- 請求使用哪些欄位?
POST /v1/messages·claude-haiku-4-5-20251001:model,messages,system,max_tokens,stream,metadataPOST /v1/responses·claude-haiku-4-5-20251001:model,input,instructions,streamPOST /v1/chat/completions·claude-haiku-4-5-20251001:model,messages,streamPOST /v1/messages·claude-haiku:model,messages,system,max_tokens,stream,metadataPOST /v1/responses·claude-haiku:model,input,instructions,streamPOST /v1/chat/completions·claude-haiku:model,messages,streamPOST /v1/messages·claude-haiku-latest:model,messages,system,max_tokens,stream,metadataPOST /v1/responses·claude-haiku-latest:model,input,instructions,streamPOST /v1/chat/completions·claude-haiku-latest:model,messages,stream- 適用哪些限制?
POST /v1/messages·claude-haiku-4-5-20251001:ctx:200000;max_out:65536;messages.min_items:1;max_tokens.minimum:1POST /v1/responses·claude-haiku-4-5-20251001:ctx:200000;max_out:65536POST /v1/chat/completions·claude-haiku-4-5-20251001:ctx:200000;max_out:65536;messages.min_items:1POST /v1/messages·claude-haiku:ctx:200000;max_out:65536;messages.min_items:1;max_tokens.minimum:1POST /v1/responses·claude-haiku:ctx:200000;max_out:65536POST /v1/chat/completions·claude-haiku:ctx:200000;max_out:65536;messages.min_items:1POST /v1/messages·claude-haiku-latest:ctx:200000;max_out:65536;messages.min_items:1;max_tokens.minimum:1POST /v1/responses·claude-haiku-latest:ctx:200000;max_out:65536POST /v1/chat/completions·claude-haiku-latest:ctx:200000;max_out:65536;messages.min_items:1