创建思考聊天

概览

• 方法: POST
• 地址: https://api.winfull.cloud-ip.cc/v1/chat/completions
• 简介: 给定一个提示，该模型将返回一个或多个预测的完成，并且还可以返回每个位置的替代标记的概率。为提供的提示和参数创建完成官方文档：https://docs.anthropic.com/en/docs/build-with-claude/extended-thinking

认证

• Header: Authorization: Bearer <token>

请求参数

• Header: Authorization: Bearer <token>
• Body 类型: application/json

{
  "model": "claude-sonnet-4-20250514",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true,
    "max_tokens": 16000,
  "thinking": {
    "type": "enabled",
    "budget_tokens": 10240
  }
}

请求示例

curl --location --request POST 'https://api.winfull.cloud-ip.cc/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "claude-sonnet-4-20250514",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true,
    "max_tokens": 16000,
  "thinking": {
    "type": "enabled",
    "budget_tokens": 10240
  }
}'

返回示例

🟢200OK 示例

{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "\n\nHello there, how may I assist you today?"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}

最后更新：2026-01-15 14:28:25