开启思考

POST

{{url}}/v1/messages

最后修改时间：2025-11-29 15:49:01

请求参数

Header 参数

Body 参数application/json

示例

{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 2048,
    "temperaure": 0.6,
    "messages": [
        {
            "role": "user",
            "content": "你好克劳德"
        }
    ],
    "thinking": {
        "type": "enabled",
        "budget_tokens": 1024
    }
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location -g --request POST 'http://api.example.com/v1/messages' \
--header 'x-api-key: sk-xxx' \
--header 'anthropic-version: 2023-06-01' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "claude-sonnet-4-5-20250929",
    "max_tokens": 2048,
    "temperaure": 0.6,
    "messages": [
        {
            "role": "user",
            "content": "你好克劳德"
        }
    ],
    "thinking": {
        "type": "enabled",
        "budget_tokens": 1024
    }
}'

返回响应

🟢200成功

application/json

Body

示例

{
    "model": "claude-sonnet-4-5-20250929",
    "id": "msg_014usLNJL8eUusKSx1CPQWEp",
    "type": "message",
    "role": "assistant",
    "content": [
        {
            "type": "thinking",
            "thinking": "The user has greeted me in Chinese, saying \"你好克劳德\" which means \"Hello Claude.\"\n\nI should respond politely in Chinese.",
            "signature": "EqgCCkYIChgCKkAFaSwVdResepgQS/Djmr6jt0u/2CTFnxtywbmgkmwFHyDG+cHmv0ZeBDYzEEjmCZvHOsuhlLL+z6jR0p+t2pw9Egz/3On7iQs7u8b5RiAaDMcGUlSss2YZtH1IXyIwqzZDjuhTrkNQhsnXhCv+XVxJeA7s4Wn33GleTg+NKVzhHIgSZNBwncwMLZVy0ESdKo8B9xOgsYb9RcQOBDy6yOAaI0Q+UJbKEX5GkNmwVEsvLbSCAGRq7BB4nzSmO6GpeKvY9CNJzIwUoEhqEjfnayqvnW1RKZ/ml9OPH/KQh6Uk/1q4QWbBqM7BiwoZl9OcuR0aEAsF7ZPYt+xxms37sLfJ3fuwUcgn5UJtvG/n5sj0yXtA4+H2toeceYFpMU/i+ioYAQ=="
        },
        {
            "type": "text",
            "text": "你好！很高兴见到你。有什么我可以帮助你的吗？"
        }
    ],
    "stop_reason": "end_turn",
    "stop_sequence": null,
    "usage": {
        "input_tokens": 43,
        "cache_creation_input_tokens": 0,
        "cache_read_input_tokens": 0,
        "cache_creation": {
            "ephemeral_5m_input_tokens": 0,
            "ephemeral_1h_input_tokens": 0
        },
        "output_tokens": 69,
        "service_tier": "standard"
    }
}

修改于 2025-11-29 15:49:01

流式请求

图像识别