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

# Wan 3.0 API

> Generate videos from text, frames, and multimodal references with Alibaba Wan 3.0.

<div className="models-color-scope" aria-hidden="true" />

Wan 3.0 is Alibaba's all-in-one video model for text-to-video, first-frame or first-and-last-frame animation, and multimodal reference generation. It produces videos up to 30 seconds with optional generated audio.

<div className="model-workflow-tabs" aria-label="Wan 3.0 endpoints">
  <a className="model-workflow-tab is-active" href="/docs/models/wan-3/text-to-video">Text to video</a>
  <a className="model-workflow-tab" href="/docs/models/wan-3/image-to-video">Image to video</a>
  <a className="model-workflow-tab" href="/docs/models/wan-3/reference-to-video">References</a>
</div>

**Default endpoint:** `POST https://api.higgsfield.ai/alibaba/wan-3.0/text-to-video`

**Endpoint ID:** `alibaba/wan-3.0/text-to-video`

<a className="model-playground-card" href="https://console.higgsfield.ai/models/alibaba%2Fwan-3.0%2Ftext-to-video/playground" target="_blank" rel="noreferrer">
  <span className="model-playground-icon">▶</span>
  <span className="model-playground-copy"><span className="model-playground-title">Try Wan 3.0</span><span>Open the default endpoint in the Higgsfield API Playground.</span></span>
  <span className="model-card-arrow">↗</span>
</a>

## Available endpoints

| Workflow                                               | Endpoint                                   |
| ------------------------------------------------------ | ------------------------------------------ |
| [Text to video](/docs/models/wan-3/text-to-video)           | `POST /alibaba/wan-3.0/text-to-video`      |
| [Image to video](/docs/models/wan-3/image-to-video)         | `POST /alibaba/wan-3.0/image-to-video`     |
| [Reference to video](/docs/models/wan-3/reference-to-video) | `POST /alibaba/wan-3.0/reference-to-video` |

## Highlights

* Generate 2–30 second videos at 480p, 720p, or 1080p.
* Animate a first frame or guide the ending with an optional last frame.
* Combine image, video, and audio references in one request.
* Use a document or public web page as creative context.
* Generate synchronized audio by default or turn it off per request.


## Related topics

- [Wan 3.0 Text to Video API](/docs/models/wan-3/text-to-video.md)
- [Wan 3.0 Image to Video API](/docs/models/wan-3/image-to-video.md)
- [Wan 3.0 Reference to Video API](/docs/models/wan-3/reference-to-video.md)
- [Kling 3.0 API](/docs/models/kling-3.md)
- [Kling 3.0 Standard Text to Video API](/docs/models/kling-3/standard-text-to-video.md)