Anthropic 訊息
透過 CometAPI 使用 Anthropic Messages API，以存取 Claude 模型的延伸思考、Prompt 快取、工具使用、網頁搜尋/擷取、串流（Streaming）與 effort control。
{
"id": "<string>",
"type": "message",
"role": "assistant",
"content": [
{
"type": "text",
"text": "<string>",
"thinking": "<string>",
"signature": "<string>",
"id": "<string>",
"name": "<string>",
"input": {}
}
],
"model": "<string>",
"stop_reason": "end_turn",
"stop_sequence": "<string>",
"usage": {
"input_tokens": 123,
"output_tokens": 123,
"cache_creation_input_tokens": 123,
"cache_read_input_tokens": 123,
"cache_creation": {
"ephemeral_5m_input_tokens": 123,
"ephemeral_1h_input_tokens": 123
}
}
}概覽
CometAPI 原生支援 Anthropic Messages API，讓你可以直接存取 Claude 模型及所有 Anthropic 專屬功能。當你需要使用 Claude 獨有的能力，例如延伸思考、Prompt 快取與 effort control 時，請使用此端點。快速開始
使用官方 Anthropic SDK——只需將 base URL 設為 CometAPI：import anthropic
client = anthropic.Anthropic(
base_url="https://api.cometapi.com",
api_key="<COMETAPI_KEY>",
)
message = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
messages=[{"role": "user", "content": "Hello!"}],
)
print(message.content[0].text)
x-api-key 與 Authorization: Bearer 標頭都支援用於驗證。官方 Anthropic SDK 預設使用 x-api-key。延伸思考
使用thinking 參數啟用 Claude 的逐步推理。回應會包含 thinking content 區塊，顯示 Claude 在最終答案之前的內部推理過程。
message = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=16000,
thinking={
"type": "enabled",
"budget_tokens": 10000,
},
messages=[
{"role": "user", "content": "Prove that there are infinitely many primes."}
],
)
for block in message.content:
if block.type == "thinking":
print(f"Thinking: {block.thinking[:200]}...")
elif block.type == "text":
print(f"Answer: {block.text}")
budget_tokens。Thinking tokens 會計入你的 max_tokens 限制，因此請將 max_tokens 設得足夠高，以容納 thinking 與回應內容。Prompt 快取
你可以快取大型 system prompts 或對話前綴，以降低後續請求的延遲與成本。請在需要快取的 content 區塊中加入cache_control：
message = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
system=[
{
"type": "text",
"text": "You are an expert code reviewer. [Long detailed instructions...]",
"cache_control": {"type": "ephemeral"},
}
],
messages=[{"role": "user", "content": "Review this code..."}],
)
usage 欄位中回報：
cache_creation_input_tokens— 寫入快取的 tokens（以較高費率計費）cache_read_input_tokens— 從快取讀取的 tokens（以較低費率計費）
串流（Streaming）
將stream: true 設定為啟用，即可使用 Server-Sent Events（SSE）進行串流回應。事件會依照以下順序到達：
message_start— 包含訊息中繼資料與初始使用量content_block_start— 標記每個內容區塊的開始content_block_delta— 遞增文字片段（text_delta）content_block_stop— 標記每個內容區塊的結束message_delta— 最終的stop_reason與完整的usagemessage_stop— 表示串流結束
with client.messages.stream(
model="claude-sonnet-4-6",
max_tokens=256,
messages=[{"role": "user", "content": "Hello"}],
) as stream:
for text in stream.text_stream:
print(text, end="")
努力程度控制
使用output_config.effort 控制 Claude 在產生回應時投入多少努力：
message = client.messages.create(
model="claude-opus-4-6",
max_tokens=4096,
messages=[
{"role": "user", "content": "Summarize this briefly."}
],
output_config={"effort": "low"}, # "low", "medium", or "high"
)
伺服器工具
Claude 支援在 Anthropic 基礎設施上執行的伺服器端工具：- Web Fetch
- Web Search
message = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
messages=[
{"role": "user", "content": "Analyze the content at https://arxiv.org/abs/1512.03385"}
],
tools=[
{"type": "web_fetch_20250910", "name": "web_fetch", "max_uses": 5}
],
)
message = client.messages.create(
model="claude-sonnet-4-6",
max_tokens=1024,
messages=[
{"role": "user", "content": "What are the latest developments in AI?"}
],
tools=[
{"type": "web_search_20250305", "name": "web_search", "max_uses": 5}
],
)
回應範例
以下是來自 CometAPI Anthropic 端點的典型回應：{
"id": "msg_bdrk_01UjHdmSztrL7QYYm7CKBDFB",
"type": "message",
"role": "assistant",
"content": [
{
"type": "text",
"text": "Hello!"
}
],
"model": "claude-sonnet-4-6",
"stop_reason": "end_turn",
"stop_sequence": null,
"usage": {
"input_tokens": 19,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"cache_creation": {
"ephemeral_5m_input_tokens": 0,
"ephemeral_1h_input_tokens": 0
},
"output_tokens": 4
}
}
與 OpenAI 相容端點的主要差異
| 功能 | Anthropic Messages (/v1/messages) | OpenAI-Compatible (/v1/chat/completions) |
|---|---|---|
| 延伸思考 | 具備 budget_tokens 的 thinking 參數 | 不支援 |
| Prompt 快取 | 內容區塊上的 cache_control | 不支援 |
| 努力程度控制 | output_config.effort | 不支援 |
| Web 擷取／搜尋 | 伺服器工具（web_fetch、web_search） | 不支援 |
| 驗證標頭 | x-api-key 或 Bearer | 僅 Bearer |
| 回應格式 | Anthropic 格式（content 區塊） | OpenAI 格式（choices、message） |
| 模型 | 僅 Claude | 多供應商（GPT、Claude、Gemini 等） |
授權
Your CometAPI key passed via the x-api-key header. Authorization: Bearer <key> is also supported.
標頭
The Anthropic API version to use. Defaults to 2023-06-01.
"2023-06-01"
Comma-separated list of beta features to enable. Examples: max-tokens-3-5-sonnet-2024-07-15, pdfs-2024-09-25, output-128k-2025-02-19.
主體
The Claude model to use. See the Models page for current Claude model IDs.
"claude-sonnet-4-6"
The conversation messages. Must alternate between user and assistant roles. Each message's content can be a string or an array of content blocks (text, image, document, tool_use, tool_result). There is a limit of 100,000 messages per request.
Show child attributes
Show child attributes
The maximum number of tokens to generate. The model may stop before reaching this limit. When using thinking, the thinking tokens count towards this limit.
x >= 11024
System prompt providing context and instructions to Claude. Can be a plain string or an array of content blocks (useful for prompt caching).
Controls randomness in the response. Range: 0.0–1.0. Use lower values for analytical tasks and higher values for creative tasks. Defaults to 1.0.
0 <= x <= 1Nucleus sampling threshold. Only tokens with cumulative probability up to this value are considered. Range: 0.0–1.0. Use either temperature or top_p, not both.
0 <= x <= 1Only sample from the top K most probable tokens. Recommended for advanced use cases only.
x >= 0If true, stream the response incrementally using Server-Sent Events (SSE). Events include message_start, content_block_start, content_block_delta, content_block_stop, message_delta, and message_stop.
Custom strings that cause the model to stop generating when encountered. The stop sequence is not included in the response.
Enable extended thinking — Claude's step-by-step reasoning process. When enabled, the response includes thinking content blocks before the answer. Requires a minimum budget_tokens of 1,024.
Show child attributes
Show child attributes
Tools the model may use. Supports client-defined functions, web search (web_search_20250305), web fetch (web_fetch_20250910), code execution (code_execution_20250522), and more.
Show child attributes
Show child attributes
Controls how the model uses tools.
Show child attributes
Show child attributes
Request metadata for tracking and analytics.
Show child attributes
Show child attributes
Configuration for output behavior.
Show child attributes
Show child attributes
The service tier to use. auto tries priority capacity first, standard_only uses only standard capacity.
auto, standard_only 回應
Successful response. When stream is true, the response is a stream of SSE events.
Unique identifier for this message (e.g., msg_01XFDUDYJgAACzvnptvVoYEL).
Always message.
message Always assistant.
assistant The response content blocks. May include text, thinking, tool_use, and other block types.
Show child attributes
Show child attributes
The specific model version that generated this response (e.g., claude-sonnet-4-6).
Why the model stopped generating.
end_turn, max_tokens, stop_sequence, tool_use, pause_turn The stop sequence that caused the model to stop, if applicable.
Token usage statistics.
Show child attributes
Show child attributes
{
"id": "<string>",
"type": "message",
"role": "assistant",
"content": [
{
"type": "text",
"text": "<string>",
"thinking": "<string>",
"signature": "<string>",
"id": "<string>",
"name": "<string>",
"input": {}
}
],
"model": "<string>",
"stop_reason": "end_turn",
"stop_sequence": "<string>",
"usage": {
"input_tokens": 123,
"output_tokens": 123,
"cache_creation_input_tokens": 123,
"cache_read_input_tokens": 123,
"cache_creation": {
"ephemeral_5m_input_tokens": 123,
"ephemeral_1h_input_tokens": 123
}
}
}