> ## Documentation Index
> Fetch the complete documentation index at: https://docs.meshrouter.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Vision and multimodal

> Send text and images to models that support visual input.

Use OpenAI-style content parts for multimodal requests.

```json theme={null}
{
  "model": "mesh/claude-sonnet-4.5",
  "messages": [
    {
      "role": "user",
      "content": [
        { "type": "text", "text": "Extract the table from this image." },
        {
          "type": "image_url",
          "image_url": { "url": "https://example.com/table.png" }
        }
      ]
    }
  ]
}
```

The model catalogue marks supported modalities so callers can choose `text`, `image`, or `audio`
capable routes.