Chat（视频识别分析） - ChatGPT API 中文文档

请求参数

Header 参数

Body 参数application/json

示例

{
  "model": "gemini-2.5-pro-thinking-128",
  "stream": true,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "这个视频讲了什么？"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://files.closeai.fans/filesystem/48/v1/videos/video_cedaa1f0-c4ac-4e18-8816-a52cb5044fd1/content.mp4"
          }
        }
      ]
    }
  ],
  "max_tokens": 4000
}

请求示例代码

Shell

JavaScript

Java

Swift

Go

PHP

Python

HTTP

C

C#

Objective-C

Ruby

OCaml

Dart

R

curl --location --request POST 'https://api.pro365.top/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer ' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "gemini-2.5-pro-thinking-128",
  "stream": true,
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "这个视频讲了什么？"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://files.closeai.fans/filesystem/48/v1/videos/video_cedaa1f0-c4ac-4e18-8816-a52cb5044fd1/content.mp4"
          }
        }
      ]
    }
  ],
  "max_tokens": 4000
}'

返回响应

🟢200OK

application/json

Body

示例

{
    "id": "chatcmpl-20251018143916102553253dwOVEGie",
    "model": "gemini-2.5-pro",
    "object": "chat.completion",
    "created": 1760769565,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "根据视频内容，这是一个关于写作的教学或分享视频。\n\n视频中的女生正在解释如何根据老师的要求写一段话。她首先展示了自己记下的课堂重点，并提到老师要求使用一个特定的结构来写作。\n\n她计划的写作步骤如下：\n1.  **准备提纲**：她会先写一个提纲，方便之后直接照着写。\n2.  **写开头句 (Topic Sentence)**：先写一个明确的开头句来引出主题。\n3.  **补充论据 (Supporting Details)**：接着用两个论据来支撑和补充开头句的观点。\n4.  **写总结句 (Concluding Sentence)**：最后用一个总结句来收尾。\n\n总的来说，这个视频简要地介绍了一个基础的段落写作结构（开头-论据-结尾），并准备演示如何运用这个结构来完成一个写作任务。",
                "reasoning_content": "**Breaking Down the Visuals**\n\nOkay, so I'm looking at this video, and the first thing I need to do is get a handle on the visual context. I see a young woman, definitely a student vibe, probably in a classroom or a library. She's got the standard gear: notebook, pen, laptop – the tools of the trade, you know? It's all very familiar territory. That's my initial frame of reference for understanding whatever content is about to unfold. Now, let's see what she's actually *doing*.\n"
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 3224,
        "completion_tokens": 247,
        "total_tokens": 3471,
        "prompt_tokens_details": {
            "cached_tokens": 0,
            "text_tokens": 7,
            "audio_tokens": 324,
            "image_tokens": 0
        },
        "completion_tokens_details": {
            "text_tokens": 0,
            "audio_tokens": 0,
            "reasoning_tokens": 53
        },
        "input_tokens": 0,
        "output_tokens": 0,
        "input_tokens_details": null
    }
}