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

# Wan 3

> Alibaba's video model, for clips up to 30 seconds and references of every kind.

Wan 3, from Alibaba, makes clips up to 30 seconds long and takes image, video
and audio references. Choose **Standard**, the default, or **Prime** under
**Tier**. Prime has the same inputs and settings, and costs more.

## What you can give it

* **A prompt** on its own.
* **Frames**: a start frame, and an optional end frame.
* **References**: up to 20, with up to 10 images, 5 videos and 5 audio clips.
  Video and audio can each total up to 15 seconds. References can't be
  combined with frames.

## Output settings

| Setting | Options |
| - | - |
| Resolution | 480p, 720p or 1080p. |
| Aspect ratio | Auto, 16:9, 4:3, 1:1, 3:4 or 9:16. |
| Duration | 2 to 30 seconds. |
| Audio | On or off. Sound doesn't change the price. |
| Quantity | 1 to 4 videos. |

## Cost

Wan 3 is priced per second of video, by tier and resolution. Reference videos
add to the price. A 5-second 720p video costs about $0.65 on the Standard tier,
or $0.91 on Prime. Prices are as of October 28, 2026.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.