会话补全（通用）

POST

/v1/chat/completions

只提供简单的请求示例，更详细的API接口使用说明请阅读官方文档
注意：OpenAI、Claude、Gemini...等聊天模型均使用该接口格式。

请求参数

Authorization

JWT Bearer

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": "gpt-5",
    "messages": [
        {
            "role": "developer",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Hello!"
        }
    ]
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST '/v1/chat/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "gpt-5",
    "messages": [
        {
            "role": "developer",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Hello!"
        }
    ]
}'

返回响应

🟢200成功

application/json

Body

示例

{
  "id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
  "object": "chat.completion",
  "created": 1741569952,
  "model": "gpt-4.1-2025-04-14",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?",
        "refusal": null,
        "annotations": []
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 19,
    "completion_tokens": 10,
    "total_tokens": 29,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    }
  },
  "service_tier": "default"
}

修改于 2025-09-23 13:51:02

列出可用模型

会话补全（图片分析）