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

# Vision and audio input

> Send images and audio to models through LLM Router chat completions, and see how the router validates and routes them.

Vision lets a model read images that you send alongside text. Some models also accept audio input. On LLM Router you send both the same way: use the array form of a message's `content`, with one typed part per piece of content.

| Part type | Shape | Used for |
|-----------|-------|----------|
| `text` | `{"type": "text", "text": "..."}` | Text. |
| `image_url` | `{"type": "image_url", "image_url": {"url": "...", "detail": "auto"}}` | Images, as a URL or a base64 data URI. |
| `input_audio` | `{"type": "input_audio", "input_audio": {"data": "...", "format": "wav"}}` | Base64-encoded audio. |

Whether a model accepts images or audio depends on the model. Refer to the provider's documentation for supported input types, formats, and limits.

## Vision

Pass the image as an HTTP(S) URL or as a base64 data URI in `image_url.url`:

```bash
curl --request POST \
  --url https://api.inworld.ai/v1/chat/completions \
  --header "Authorization: Basic $INWORLD_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "google-ai-studio/gemini-2.5-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Describe this image." },
          { "type": "image_url", "image_url": { "url": "data:image/jpeg;base64,/9j/4AAQ..." } }
        ]
      }
    ]
  }'
```

`image_url.detail` is optional and defaults to `auto`.

### Image URLs on Google models

Google AI Studio and Vertex AI do not fetch images from HTTP(S) URLs. Send those models a base64 data URI.

The router checks this against the models a request can reach:

- If every candidate model is served by Google, an HTTP(S) image URL returns `400`.
- If the request can also reach a model from another provider, for example through [fallbacks](https://docs.inworld.ai/router/core-concepts/overview.md#fallbacks) or `model: "auto"`, the router uses that model instead.

A data URI works on every provider, so prefer it when a request can route to more than one.

## Audio input

Pass base64-encoded audio in `input_audio.data` and name its format:

```bash
curl --request POST \
  --url https://api.inworld.ai/v1/chat/completions \
  --header "Authorization: Basic $INWORLD_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "google-ai-studio/gemini-2.5-flash",
    "messages": [
      {
        "role": "user",
        "content": [
          { "type": "text", "text": "Transcribe this audio." },
          { "type": "input_audio", "input_audio": { "data": "UklGRi...", "format": "wav" } }
        ]
      }
    ]
  }'
```

The router passes `format` to the provider without checking it, so the formats you can use are the ones the model accepts. Anthropic models do not take audio input: the audio part is left out of the request and the model sees only the rest of the message.

<Tip>
  To transcribe speech, [Inworld STT](https://docs.inworld.ai/stt/overview.md) is the dedicated API. To hold a spoken conversation with a model, use the [Realtime API](https://docs.inworld.ai/realtime/overview.md).
</Tip>

## Validation

- A data URI in `image_url` must have an `image/*` media type, and one in `input_audio` an `audio/*` media type. Anything else returns `400`.
- Video input is not supported and returns `400`.
- Content parts of any other type, such as `file`, are skipped rather than rejected. The request can succeed without the model having seen that part, so check that every part you send is one of the three types above.

## How routing uses input types

- With `model: "auto"`, the router only considers models that accept the input types in your request.
- With a named model, that model is always tried, and only its fallbacks are filtered by input type.

## Related

- [Voice responses](https://docs.inworld.ai/router/guides/llm-plus-tts.md) return spoken audio from a chat completion.
- [Chat completions](https://docs.inworld.ai/router/capabilities/text-chat.md) covers the request basics.
- [API reference](https://docs.inworld.ai/api-reference/routerAPI/chat-completions.md) lists every parameter.