Wan 3.0 is the newest video model in Alibaba’s Wanxiang family. It supports text-to-video, first frame and first-and-last-frame video, with native audio.

Does audio cost extra?

No. The audio track is included at the same price.

Does a longer clip cost more?

Yes — video is priced per second, so a 10-second clip costs twice a 5-second one.

Video model · Alibaba

Wan 3.0 — Alibaba’s Newest AI Video Model

Text, first-frame and first+last-frame video with native audio, from Alibaba Wanxiang.

Try Wan 3.0 See examples

Try a prompt

A kitten runs across a moonlit rooftop, neon city lights flickering behind it, cinematic Slow dolly through a rainy night market, steam rising from food stalls A paper boat drifting down a puddle-filled street after a storm, soft morning light

Made with Wan 3.0

Sample clips

Key features

5 highlights

Text-to-video and image-to-video

First and last frame control

Native audio included

720p, 2–10 second clips

Priced per second of video

Specifications

Capabilities &
supported configs

Resolution720p
Duration2–10 seconds
Aspect ratios16:9, 4:3, 1:1, 3:4, 9:16
AudioAutomatic sound generation
Start frameSupported
End frameSupported

FAQ

Frequently asked

Ready to try Wan 3.0?

Start generating with free credits. No credit card required.

Try Wan 3.0

Wan 3.0 — Alibaba’s Newest AI Video Model

Wan 3.0 — Alibaba’s Newest AI Video Model

Made with Wan 3.0

Key features

Capabilities &supported configs

Frequently asked

Ready to try Wan 3.0?

Capabilities &
supported configs