Wan 3.0Top

Alibaba · Video · 2–30s · 480p–1080p

API
Saved
Example

Your video will appear here

Fill in the settings and press Run. The result is also saved to your library.

Price

Reference price

No published price yet - this model is not in the public price list.

What the price depends on

  • This model is billed per second of output, so length is the biggest lever on the price.
  • Resolution and quality settings change the price. Change one and the number above follows.
  • A generation the provider fails is not charged. A chat answer is charged for what the model wrote and thought, even if you stop it.

Prices are in credits. What a credit costs is on the pricing page.

Which one to pick

ModelKey specsPrice from
Wan 3.0 Prime2–30s · 480p–1080p—
Wan 3.0Top· you are here2–30s · 480p–1080p—
Happy Horse 1.13–15s · 720p, 1080p—
Wan 2.75, 10, 15s · 720p, 1080p—
Happy Horse3–15s · 720p, 1080p—
Wan 2.65, 10, 15s · 720p, 1080p—
Wan Animate480p–720p—

About the model

Alibaba Wan 3.0: 2 to 30 seconds at 480p to 1080p, with generated sound, from a prompt, frames or references.

Produces
Video
Takes
text, pictures, sound, video
Length
from 2s to 30s
Frame shape
Like the picture, 16:9, 4:3, 1:1, 3:4, 9:16, 21:9
Resolution
480p, 720p, 1080p

What you can set

Every setting of this model and the choices it allows — the same as in the form.

  • Input images
    up to 2 files
  • Sound reference
    up to 5 files
  • Style references
    up to 10 files
  • Motion reference
    up to 5 files
  • Aspect ratio
    Like the picture16:94:31:13:49:1621:9
  • Duration
    from 2s to 30s
  • Resolution
    480p720p1080p
  • Audio setting
    Add a soundtrack to the clip.
  • Seed
    from 0 to 2147483647

For developers

Run this from your own code

The same request the Generate tab sends, with the settings you have chosen.

Model id:wan-3
curl -X POST https://seedara.ai/api/v1/generate \
  -H "Authorization: Bearer $SEEDARA_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
  "model": "wan-3",
  "prompt": "Describe the shot: subject, action, camera move, lighting...",
  "params": {
    "aspect_ratio": "adaptive",
    "duration_seconds": 5,
    "resolution": "720p",
    "audio": true
  }
}'

This snippet updates as you change the form. Copy it once the settings are the ones you want.

Request parameters

What goes in `params`, by the names the API uses.

Optional

Left out unless you set them - the provider then applies its own default.

ParameterTypeAccepted valuesDefault
image_urls

Input images

imagesup to 2 files—
reference_audio_urls

Sound reference

audio filesup to 5 files—
reference_image_urls

Style references

imagesup to 10 files—
reference_video_urls

Motion reference

videosup to 5 files—
aspect_ratio

Aspect ratio

one of a listadaptive16:94:31:13:49:1621:9adaptive
duration

Duration

whole numberany value from 2 to 305
resolution

Resolution

one of a list480p720p1080p720p
audio

Audio setting

on / off—true
seed

Seed

whole numberany value from 0 to 2147483647—

Available through the API only

These take structured objects that no single control can express, so the form leaves them out rather than half-supporting them.

reference_file_urlsreference_link_urls

How a generation runs

  1. POST /v1/generate answers immediately with a job_id - it does not wait for the result.
  2. Poll GET /v1/jobs/{id} until status is completed or failed.
  3. A completed job carries output_url - the finished file.
curl https://seedara.ai/api/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $SEEDARA_API_KEY"
Questions

Frequently asked about Wan 3.0

New
Start now

Your first video —
in a minute

Describe what you want to see — the model does the rest.

Takes you to the settings — prompt, format and price are already there
  • No auto-charges
  • Pay only for a finished result
  • Works are kept in your Library
100credits as a gift
2–30sLength
adaptive · 16:9 · 4:3Frame shape