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

# Multimodality

> Use text, image, audio, video, and other modalities through the Gateway.

The Gateway exposes multiple modalities through a unified API surface. Each endpoint maps to a different capability, and model support varies by provider.

## Modalities and endpoints

| Modality                     | Primary endpoints                                                                                        | Notes                                                                        |
| ---------------------------- | -------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------- |
| Text                         | `/v1/responses`, `/v1/chat/completions`, `/v1/messages`                                                  | Structured and conversational outputs.                                       |
| Images                       | `/v1/images/generations`, `/v1/images/edits`                                                             | Text-to-image and image editing.                                             |
| Audio (TTS/STT/Translations) | `/v1/audio/speech`, `/v1/audio/transcriptions`, `/v1/audio/translations`                                 | Text-to-speech, speech-to-text, and spoken-audio translation.                |
| Video                        | `/v1/videos`, `/v1/videos/{video_id}`, `/v1/videos/{video_id}/content`, `/v1/videos/{video_id}` (DELETE) | Create asynchronous video jobs, poll status, fetch content, and delete jobs. |
| Music                        | `/v1/music/generate`                                                                                     | Music generation via supported providers.                                    |
| OCR                          | `/v1/ocr`                                                                                                | Extract text from images where supported.                                    |

## Checking model support

Use the [Models endpoint](../api-reference/endpoint/models.mdx) to see which models are available and which endpoints they support. Provider coverage is available via the [Providers endpoint](../api-reference/endpoint/providers.mdx).

## Best practices

* Match the endpoint to the modality you need, even if the model name is shared across modalities.
* Validate payloads against the [API Reference](../api-reference/introduction.mdx) before shipping.