Chat Completions - 视觉（图片理解）

POST

/v1/chat/completions

OpenAI Vision - 通过 URL 传入图片进行多模态理解

Request

Header Params

Body Params application/json

Examples

Responses

🟢200

application/json

Body

Request Example

Shell

JavaScript

Java

Swift

curl --location --request POST 'https://newapi.mexxxxai.win/v1/chat/completions' \
--header 'Authorization: Bearer {{OPENAI_API_KEY}}' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": [
        {"type": "text", "text": "这张图片里有什么？"},
        {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/PNG_transparency_demonstration_1.png/280px-PNG_transparency_demonstration_1.png", "detail": "auto"}}
      ]
    }
  ],
  "max_tokens": 1024
}'

Response Example

{
  "id": "chatcmpl-vision001",
  "object": "chat.completion",
  "created": 1743580800,
  "model": "gpt-4o-2024-08-06",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "这张图片展示了 PNG 透明度演示图，图中有一只骰子和一个棋盘格背景图案，用于演示 PNG 图像格式的透明通道（Alpha 通道）功能。棋盘格部分代表透明区域。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1105,
    "completion_tokens": 62,
    "total_tokens": 1167
  }
}

Modified at 2026-04-02 11:32:32

Chat Completions - 多轮对话

Responses - 基础文本生成