Wan 3.0 API

Wan 3.0 video with native audio, up to 30 seconds in one shot — from a text prompt, from a first frame with an optional last frame, or from reference images that keep subjects consistent

Endpoint

POST https://api.hedra.com/v3/models/wan-3-0

Example request

curl -X POST "https://api.hedra.com/v3/models/wan-3-0" \
  -H "Authorization: Key $HEDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"input": {"prompt": "a cinematic shot of a city at dusk"}}'

Parameters

num_outputsinteger

Number of outputs generated per job. Only 1 is supported.

promptstringrequired

Generation prompt. At most 5000 characters.

aspect_ratiostringrequired

Output aspect ratio.

resolutionstringrequired

Output resolution.

duration_msintegerrequired

Duration in ms.

generate_audioboolean

Whether to generate native audio for the video.

seedinteger

Seed for reproducible output; omit for a random seed. From 0 to 2147483647.

start_image

Start frame (image-to-video). At most 20 MB.

end_image

End frame (first-last-frame-to-video). At most 20 MB.

imagesarray

Reference images. 1 to 10 images, each at most 20 MB.

videosarray

Reference videos. 1 to 5 videos, each at most 15s and at most 524.2 MB, at most 15s in total.

audiosarray

Reference audios. 1 to 5 audio files, each at most 15s and at most 104.8 MB, at most 15s in total.

qualitystringrequired

Quality level to generate at.