控制推理模型努力程度

POST

/v1/chat/completions

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://platform.openai.com/docs/guides/reasoning?api-mode=responses

请求参数

Authorization

在 Header 添加参数

Authorization

，其值为在 Bearer 之后拼接 Token

示例：

Authorization: Bearer ********************

Header 参数

Body 参数application/json

示例

{
  "model": "o4-mini",
  "max_tokens": 500,
  "messages": [
    {
      "role": "user",
      "content": "你好"
    }
  ],
  "temperature": 1.0,
  "stream": true,
  "reasoning_effort":"medium"
 
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
  "model": "o4-mini",
  "max_tokens": 500,
  "messages": [
    {
      "role": "user",
      "content": "你好"
    }
  ],
  "temperature": 1.0,
  "stream": true,
  "reasoning_effort":"medium"
 
}'

返回响应

🟢200OK

application/json

Bodyapplication/json

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
    }
}

修改于 2026-04-15 06:19:08

创建结构化输出

创建聊天补全 qwen-mt-turbo