> For the complete documentation index, see [llms.txt](https://anyint.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://anyint.gitbook.io/docs/models-and-modalities/overview.md).

# overview

AnyInt currently exposes multimodal capabilities through several route families instead of one single abstraction layer. The main decision is whether you need image understanding, image generation, video generation, or full music creation workflows.

## Current multimodal surfaces

| Surface                       | Best for                                                          | Sync or task-based                    |
| ----------------------------- | ----------------------------------------------------------------- | ------------------------------------- |
| Anthropic-compatible messages | text plus image understanding                                     | sync                                  |
| Gemini-compatible routes      | text generation, image generation, Gemini-native function flows   | sync or streaming                     |
| DashScope media routes        | prompt-driven image and video generation                          | sync for images, task-based for video |
| AI Music                      | song generation, covers, lyrics, stems, and music video workflows | task-based                            |

## How to choose

* Need image understanding inside a message flow: start with Anthropic-compatible messages
* Need generated images: use Gemini image generation or DashScope image generation
* Need prompt-driven video: use DashScope video generation
* Need music creation or transformation: use AI Music

## Sync vs async matters

Not every multimodal route is synchronous:

* image generation can return usable content in one response
* video and music workflows usually involve tasks, polling, and webhooks

That affects UI design, retry logic, and how you store outputs.