联网模型识别文件

POST

/v1/chat/completions

将文件链接放在开头 + 空格 + 提示词，只有 gpt-4o-all 和 gpt-4-all 模型支持识别文件功能，能识别图片、识别 PDF、识别 Word 文档等文件

请求参数

Header 参数

Body 参数application/json必填

示例

{
  "model": "gpt-4o-all",
  "stream": false,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png 这张图片有什么"
        }
      ]
    }
  ]
}

请求示例代码

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/chat/completions' \
--header 'Authorization;' \
--header 'Content-Type: application/json' \
--data '{
  "model": "gpt-4o-all",
  "stream": false,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png 这张图片有什么"
        }
      ]
    }
  ]
}'

返回响应

🟢200成功

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 2026-05-07 08:54:47

原生Claude聊天对话格式

gpts