Analyze images with Meridian vision

Pass image URLs directly to gpt-4o or azure-swc/gpt-4.1 for classification, captioning, OCR, and structured extraction.

Quick start

POST /v1/chat/completions
Content-Type: application/json

{
  "model": "gpt-4o",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://example.com/photo.jpg"
          }
        }
      ]
    }
  ]
}

image_url parts

The image_url content part accepts a url field pointing to a publicly accessible image. Supported formats: PNG, JPEG, WEBP, GIF (non-animated).

{
  "type": "image_url",
  "image_url": {
    "url": "https://example.com/receipt.png",
    "detail": "high"
  }
}

Set detail to low, high, or auto (default).

Multiple images

Include multiple image_url parts in a single message to compare or analyze several images at once.

"content": [
  { "type": "text", "text": "Compare these two screenshots." },
  { "type": "image_url", "image_url": { "url": "https://..." } },
  { "type": "image_url", "image_url": { "url": "https://..." } }
]

Supported models

gpt-4o— high-accuracy vision, default choice
azure-swc/gpt-4.1— Azure deployment, identical vision capabilities

← All examples Structured outputs →