GPT-4 Vision API - 通过 UniterRouter 使用 GPT-4o、GPT-4-turbo 分析图像。图像理解、OCR、图表分析等多模态 AI 应用。

视觉

使用多模态模型（如 GPT-4o、Claude 3.5 Sonnet 或 Gemini）通过标准 Chat Completions API 分析图像。

支持的模型: GPT-4o, GPT-4 Turbo, Claude 3.5 Sonnet/Haiku, Gemini 2.0/1.5 Pro 等视觉模型。

图像输入方式

URL 引用

{
  "role": "user",
  "content": [
    {"type": "text", "text": "这张图片里有什么？"},
    {"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
  ]
}

Base64 编码

{
  "role": "user",
  "content": [
    {"type": "text", "text": "描述这张图片"},
    {
      "type": "image_url",
      "image_url": {
        "url": "data:image/jpeg;base64,/9j/4AAQSkZJRg..."
      }
    }
  ]
}

示例请求

from openai import OpenAI
import base64

client = OpenAI(
    base_url="https://api.uniterouter.ai/v1",
    api_key="your_api_key",
)

# 使用 URL
response = client.chat.completions.create(
    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://example.com/photo.jpg"}
                }
            ]
        }
    ],
    max_tokens=300
)

# 使用 Base64
with open("image.jpg", "rb") as f:
    image_data = base64.b64encode(f.read()).decode()

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "描述这张图片"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": f"data:image/jpeg;base64,{image_data}"
                    }
                }
            ]
        }
    ]
)

import OpenAI from "openai";
import * as fs from "fs";

const client = new OpenAI({
  baseURL: "https://api.uniterouter.ai/v1",
  apiKey: process.env.UNITEROUTER_API_KEY,
});

// 使用 URL
const response = await client.chat.completions.create({
  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://example.com/photo.jpg" },
        },
      ],
    },
  ],
  max_tokens: 300,
});

// 使用 Base64
const imageData = fs.readFileSync("image.jpg").toString("base64");

const response2 = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    {
      role: "user",
      content: [
        { type: "text", text: "描述这张图片" },
        {
          type: "image_url",
          image_url: { url: `data:image/jpeg;base64,${imageData}` },
        },
      ],
    },
  ],
});

curl https://api.uniterouter.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $UNITEROUTER_API_KEY" \
  -d '{
    "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://example.com/image.jpg"}}
        ]
      }
    ],
    "max_tokens": 300
  }'

多图像分析

在单个请求中分析多张图像：

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "比较这两张图片"},
                {"type": "image_url", "image_url": {"url": "https://example.com/image1.jpg"}},
                {"type": "image_url", "image_url": {"url": "https://example.com/image2.jpg"}}
            ]
        }
    ]
)

图像细节级别

控制图像处理精度：

{
  "type": "image_url",
  "image_url": {
    "url": "https://example.com/image.jpg",
    "detail": "high"  // "low", "high", 或 "auto"
  }
}

级别	描述	使用场景
`low`	512px，更快，更少 token	快速分类
`high`	完整分辨率，更多细节	OCR，详细分析
`auto`	模型自动决定	通用（默认）

支持的格式

格式	MIME 类型
JPEG	`image/jpeg`
PNG	`image/png`
GIF	`image/gif`
WebP	`image/webp`

使用场景

场景	示例提示
OCR	"提取图片中的所有文字"
物体检测	"列出你能看到的所有物体"
图像描述	"详细描述这张图片"
图像对比	"这两张图片有什么区别？"
图表分析	"分析这个图表并总结数据"
代码截图	"将这个代码截图转换为文字"

限制

最大图像尺寸因模型而异
部分模型限制每次请求的图像数量
动态 GIF 仅使用第一帧

视觉

视觉