Wan 3.0

Alibaba · Video model
Text to video · Image to videoNative audioStarter and above

Open-weight leader with audio, clips up to 30 seconds.

Model IDwan-3.0
Made with Wan 3.0“A street musician plays saxophone under a bridge at night, warm streetlight, passersby, jazzy music”
Per second
$0.208
at 1080p, with the 4% plan fee
5s clip
$1.04
at default settings · 1080p
Provider price
$0.0500
per second · synced 2026-11-08
Plan
Starter+
From $20/month · usage included

You pay the provider’s metered cost plus your plan fee (4% on paid plans), and your plan’s included weekly usage applies first. Resolution, length and audio change the metered cost; the playground shows an estimate before you generate. Prices follow the provider’s live price list.

Controls

The same settings work in the playground and through the API.

Duration

2–30 seconds

Aspect ratio

16:94:31:13:49:16

Resolution

480p720p1080p

Audio

Native audio, on by default

Image to video

Start frame and last frame

Negative prompt

Not supported

Use it from the API

Submit a job, then poll it until the video is ready (usually one to five minutes). Add "image": "LIBRARY_IMAGE_ID" to animate a start frame.

POST /api/v1/videos/generations
curl https://api.gizmoplatforms.com/api/v1/videos/generations \
  -H "Authorization: Bearer $GIZMO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "wan-3.0",
  "prompt": "A street musician plays saxophone under a bridge at night, warm streetlight, passersby, jazzy music",
  "settings": {
    "duration": 5,
    "aspect": "16:9",
    "resolution": "1080p",
    "audio": true
  }
}'
GET /api/v1/videos/generations/:id
curl https://api.gizmoplatforms.com/api/v1/videos/generations/REQUEST_ID \
  -H "Authorization: Bearer $GIZMO_API_KEY"

Full video API reference →

More video models