Wan 3.0

WAN 3.0 generates video from text, a start frame, or reference media, with optional native audio and clips from 2 to 30 seconds.

Price is per video output second, rounded up.

Offering

Price

480p

$0.05

720p

$0.10

1080p

$0.20

Reference video (per input second) · 480p

$0.05

Reference video (per input second) · 720p

$0.10

Reference video (per input second) · 1080p

$0.20

Call the API endpoint to get the latest, detailed pricing and pricing estimates.

Wan 3.0

Wan 3.0 is Alibaba’s video model from the Tongyi Wanxiang group. It went public in 2026, around August. You can generate from a prompt, from a start frame, or from reference images, videos, and audio. Native audio is optional.

Clips run from 2 to 30 seconds at 480p, 720p, or 1080p. Aspect ratios are 16:9, 9:16, 1:1, 4:3, and 3:4. Prompt expansion can be turned on per request.

Thirty seconds is a single continuous generate, not several clips stitched together. Two seconds is available as well, for a single beat.

What it's good for

A video that needs to run longer than a typical eight-second cinematic shot: a walk across a room, a demonstration with a beginning and an end, a slow reveal. Also useful when the output has to be square or vertical, since those aspect ratios are first-class here, not a crop after the fact.

Model ID

alibaba/wan-3.0

Output Type

Video

Pricing

From $0.05/s

Provider

Alibaba

Hosting

Protoface

Wan 3.0

Clips run from 2 to 30 seconds at 480p, 720p, or 1080p. Aspect ratios are 16:9, 9:16, 1:1, 4:3, and 3:4. Prompt expansion can be turned on per request.

Thirty seconds is a single continuous generate, not several clips stitched together. Two seconds is available as well, for a single beat.