Anthropic 消息 - CometAPI Documentation

POST

messages

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,
    system="You are a helpful assistant.",
    messages=[
        {"role": "user", "content": "Hello, world"}
    ],
)

print(message.content[0].text)

{
  "id": "<string>",
  "content": [
    {
      "text": "<string>",
      "thinking": "<string>",
      "signature": "<string>",
      "id": "<string>",
      "name": "<string>",
      "input": {}
    }
  ],
  "model": "<string>",
  "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
    }
  }
}

CometAPI 原生支持 Anthropic Messages API，让你能够直接访问 Claude 模型及所有 Anthropic 特有功能。对于扩展思考、Prompt 缓存和 effort control 等 Claude 专属能力，请使用此端点。

支持使用 x-api-key 和 Authorization: Bearer 请求头进行身份验证。官方 Anthropic SDK 默认使用 x-api-key。

快速开始

要通过 CometAPI 使用官方 Anthropic SDK，请设置 base URL：

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)

启用扩展思考

使用 thinking 参数启用 Claude 的逐步推理。响应中会包含 thinking 内容块，用于在最终答案之前展示 Claude 的内部推理过程。

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}")

Thinking 要求最少 budget_tokens 为 1,024。Thinking Token 会计入你的 max_tokens 限制——请将 max_tokens 设得足够高，以同时容纳 thinking 和响应内容。

缓存 Prompt

为减少后续请求的延迟和成本，你可以缓存较大的 system Prompt 或对话前缀。为需要缓存的内容块添加 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..."}],
)

缓存使用情况会在响应的 usage 字段中报告：

cache_creation_input_tokens — 写入缓存的 tokens（按更高费率计费）
cache_read_input_tokens — 从缓存读取的 tokens（按较低费率计费）

Prompt 缓存要求被缓存的内容块至少包含 1,024 tokens。短于此长度的内容不会被缓存。

流式输出响应

要使用 Server-Sent Events (SSE) 进行流式输出（Streaming）响应，请设置 stream: true。事件会按以下顺序到达：

message_start — 包含消息元数据和初始 usage
content_block_start — 标记每个内容块的开始
content_block_delta — 增量文本分块（text_delta）
content_block_stop — 标记每个内容块的结束
message_delta — 最终的 stop_reason 和完整的 usage
message_stop — 表示流结束

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="")

控制 effort

要控制 Claude 在生成响应时投入多少 effort，请使用 output_config.effort：

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"
)

使用服务器工具

Claude 支持运行在 Anthropic 基础设施上的服务端工具：

Web Fetch
Web Search

从 URL 获取并分析内容：

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}
    ],
)

在网络上搜索实时信息：

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}
    ],
)

响应示例

来自 CometAPI 的 Anthropic 端点的典型响应：

{
  "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
  }
}

与 OpenAI-compatible endpoint 对比

功能	Anthropic 消息 (`/v1/messages`)	OpenAI-Compatible (`/v1/chat/completions`)
扩展思考	带有 `budget_tokens` 的 `thinking` 参数	不可用
Prompt 缓存	内容块上的 `cache_control`	不可用
effort 控制	`output_config.effort`	不可用
Web 获取/搜索	服务端工具（`web_fetch`、`web_search`）	不可用
认证头	`x-api-key` 或 `Bearer`	仅 `Bearer`
响应格式	Anthropic 格式（`content` 块）	OpenAI 格式（`choices`、`message`）
模型	仅 Claude	多提供商（GPT、Claude、Gemini 等）

授权

x-api-key

string

header

必填

Your CometAPI key passed via the x-api-key header. Authorization: Bearer <key> is also supported.

请求头

anthropic-version

string

默认值:2023-06-01

The Anthropic API version to use. Defaults to 2023-06-01.

示例:

"2023-06-01"

anthropic-beta

string

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.

请求体

application/json

model

string

必填

The Claude model to use. See the Models page for current Claude model IDs.

示例:

"claude-sonnet-4-6"

messages

object[]

必填

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

max_tokens

integer

必填

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.

必填范围: x >= 1

示例:

1024

system

System prompt providing context and instructions to Claude. Can be a plain string or an array of content blocks (useful for prompt caching).

temperature

number

默认值:1

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.

必填范围: 0 <= x <= 1

top_p

number

Nucleus 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.

必填范围: 0 <= x <= 1

top_k

integer

Only sample from the top K most probable tokens. Recommended for advanced use cases only.

必填范围: x >= 0

stream

boolean

默认值:false

If 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.

stop_sequences

string[]

Custom strings that cause the model to stop generating when encountered. The stop sequence is not included in the response.

thinking

object

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

tools

object[]

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

tool_choice

object

Controls how the model uses tools.

Show child attributes

metadata

object

Request metadata for tracking and analytics.

Show child attributes

output_config

object

Configuration for output behavior.

Show child attributes

service_tier

enum<string>

The service tier to use. auto tries priority capacity first, standard_only uses only standard capacity.

可用选项:

auto,

standard_only

响应

200 - application/json

Successful response. When stream is true, the response is a stream of SSE events.

string

Unique identifier for this message (e.g., msg_01XFDUDYJgAACzvnptvVoYEL).

type

enum<string>

Always message.

可用选项:

message

role

enum<string>

Always assistant.

可用选项:

assistant

content

object[]

The response content blocks. May include text, thinking, tool_use, and other block types.

Show child attributes

model

string

The specific model version that generated this response (e.g., claude-sonnet-4-6).

stop_reason

enum<string>

Why the model stopped generating.

可用选项:

end_turn,

max_tokens,

stop_sequence,

tool_use,

pause_turn

stop_sequence

string | null

The stop sequence that caused the model to stop, if applicable.

usage

object

Token usage statistics.

Show child attributes

响应

Gemini 生成内容

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,
    system="You are a helpful assistant.",
    messages=[
        {"role": "user", "content": "Hello, world"}
    ],
)

print(message.content[0].text)

{
  "id": "<string>",
  "content": [
    {
      "text": "<string>",
      "thinking": "<string>",
      "signature": "<string>",
      "id": "<string>",
      "name": "<string>",
      "input": {}
    }
  ],
  "model": "<string>",
  "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
    }
  }
}

Documentation Index

​快速开始

​启用扩展思考

​缓存 Prompt

​流式输出响应

​控制 effort

​使用服务器工具

​响应示例

​与 OpenAI-compatible endpoint 对比

授权

请求头

请求体

响应

快速开始

启用扩展思考

缓存 Prompt

流式输出响应

控制 effort

使用服务器工具

响应示例

与 OpenAI-compatible endpoint 对比