Skip to main content

Image Inputs

NagaAI supports image input for vision-capable models (OpenAI, Claude, Gemini, and others). You can send images in Chat Completions using the image_url content block. Images can be provided as direct URLs or as base64-encoded data.

  • detail controls quality: low, high, or auto (default low).

How to Send Images​

Using Image URLs​

This is the most efficient way for publicly accessible images.

{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "Describe this image briefly." },
        {
          "type": "image_url",
          "image_url": {
            "url": "https://upload.wikimedia.org/wikipedia/commons/f/f5/Example_image.jpg",
            "detail": "auto"
          }
        }
      ]
    }
  ]
}

Using Base64-Encoded Images​

For local or private images, encode the image as base64 and use a data URL:

{
  "model": "gpt-4o-mini",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "What's in this image?" },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD...",
            "detail": "auto"
          }
        }
      ]
    }
  ]
}

Multiple Images​

Send multiple image_url blocks in the same message to provide several images for comparison or analysis.

Supported Image Types​

  • image/png
  • image/jpeg
  • image/webp
  • image/gif

Discover Supported Models​

You can see which models accept image inputs on the NagaAI Models page (image filter).