# Vision

Source: https://staging-docs.aiand.com/capabilities/vision/

Vision-capable models accept image inputs alongside text. ai& supports three input modes; choose the one that fits your use case.

## Three ways to send an image

<Tabs>
<TabItem label="Public URL">

```json
{
  "role": "user",
  "content": [
    { "type": "text", "text": "What's in this image?" },
    { "type": "image_url", "image_url": { "url": "https://example.com/cat.png" } }
  ]
}
```

</TabItem>
<TabItem label="Base64 inline">

```json
{
  "role": "user",
  "content": [
    { "type": "text", "text": "What's in this image?" },
    { "type": "image_url", "image_url": { "url": "data:image/png;base64,iVBORw0KG..." } }
  ]
}
```

</TabItem>
<TabItem label="Uploaded file_id">

```json
{
  "role": "user",
  "content": [
    { "type": "text", "text": "What's in this image?" },
    { "type": "file", "file": { "file_id": "file-abc123" } }
  ]
}
```

</TabItem>
</Tabs>

## The file_id path

When you send `{type: "file", file: {file_id}}`, the model receives the bytes you uploaded — no public hosting required. The wire format on your end stays the same regardless of which mode you use.

Upload images via [Files](/api/files/) with `purpose: "vision"` — or omit the purpose and let it be inferred from MIME.

Supported MIME types: `image/png`, `image/jpeg`, `image/webp`, `image/gif`. Max size: 100 MB.

## Capability gating

Vision requests are rejected if the target model lacks the `vision` capability — both for inline `image_url` parts and for `file_id` references whose purpose maps to vision. List models and their capabilities via [Models](/api/models/).

<Aside type="tip">
  Use `file_id` references for repeated requests against the same image — no re-upload, no growing payload size.
</Aside>