Responses - 视觉（图片 + 文本）

POST

/v1/responses

OpenAI Responses API - 多模态输入，图片理解

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/responses' \
--header 'Authorization: Bearer {{OPENAI_API_KEY}}' \
--header 'Content-Type: application/json' \
--data-raw '{
  "model": "gpt-4o",
  "input": [
    {
      "role": "user",
      "content": [
        {"type": "input_text", "text": "请描述这张图片的内容。"},
        {"type": "input_image", "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/PNG_transparency_demonstration_1.png/280px-PNG_transparency_demonstration_1.png"}
      ]
    }
  ]
}'

Response Example

{
  "id": "resp_vision002",
  "object": "response",
  "created_at": 1743580800,
  "model": "gpt-4o-2024-08-06",
  "output": [
    {
      "type": "message",
      "id": "msg_004",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "这张图片是一个 PNG 透明度演示图，展示了一个骰子悬浮在棋盘格背景上。棋盘格图案（灰白交替的方格）是图像编辑软件中表示透明区域的通用视觉标准，说明该图像具有透明背景（Alpha 通道）。骰子本身是不透明的，背景则是完全透明的。"
        }
      ]
    }
  ],
  "usage": { "input_tokens": 1089, "output_tokens": 78, "total_tokens": 1167 },
  "status": "completed"
}

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

Responses - 流式输出 (Stream)

Gemini - 文本生成（generateContent）