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

# Video models

> Video generation model behavior.

Video models are asynchronous by default.

They may support different combinations of:

* Text input.
* Image reference input.
* Video reference input.
* Audio reference input.
* Duration choices.
* Resolution choices.
* Aspect ratio choices.

APIAny.AI validates public request parameters before execution, so unsupported model options fail clearly.

## Available models

| Model ID            | Description                                                                                      |
| ------------------- | ------------------------------------------------------------------------------------------------ |
| `veo3-1-quality`    | Google Veo 3.1 Quality — high-fidelity video generation with native audio.                       |
| `veo3-1-quality-4k` | Google Veo 3.1 Quality 4K — top-fidelity 4K video generation with native audio.                  |
| `veo3-1-fast`       | Google Veo 3.1 Fast — rapid text-to-video generation with native audio.                          |
| `veo3-1-fast-4k`    | Google Veo 3.1 Fast 4K — fast video generation delivered at 4K resolution.                       |
| `veo3-1-fast-ref`   | Google Veo 3.1 Fast (reference) — fast video generation guided by reference images.              |
| `veo3-1-lite`       | Google Veo 3.1 Lite — an economical Veo 3.1 tier for high-volume video generation.               |
| `seedance-2.0-pro`  | Seedance 2.0 Pro — premium-tier Seedance video generation with higher fidelity and longer clips. |
| `seedance-2.0`      | Seedance 2.0 — high-quality text- and image-to-video generation via Volcengine Ark.              |
| `seedance-1.5-pro`  | Seedance 1.5 Pro — enhanced Seedance video generation with improved motion and detail.           |
| `seedance-1.0`      | Seedance 1.0 — fast, cost-effective text- and image-to-video generation.                         |
| `gemini-omni-t2v`   | Google Gemini Omni text-to-video generation through APIPod.                                      |
| `gemini-omni-i2v`   | Google Gemini Omni image-to-video generation through APIPod with 1-3 reference images.           |