Videofrom$0.0625 / s

Wan 3.0

Generates video from text, an image, references · 480p to 1080p · 2–30 s · native audio

text-to-videoimage-to-videoreference-to-video

curl -X POST https://api.open.sume.com/v1/video-router/generate \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"wan-3.0","prompt":"A cinematic tracking shot along a sunlit coastal road","duration":5,"resolution":"480p","aspect_ratio":"16:9","generate_audio":false}'

Input

prompt * · What happens in the video.duration · Seconds, 2–30.resolution · Output resolution.aspect_ratio · Frame shape.generate_audio · Generate a soundtrack with the video.Off

Advanced settings · media inputs

image_url · First frame (HTTPS image).end_image_url · Last frame (HTTPS image).reference_image_urls · Reference images (HTTPS).reference_video_urls · Reference videos (HTTPS).

Pricing…

Result

Example made with Wan 3.0 on Sume. Runs are billed to your open.sume.com balance at the price shown; failed runs are refunded.

Pricing

Dollars per unit at each option: the serving route's cost × 1.25, rounded up to $0.0001. The estimate above is the exact charge.

Option	Price
480p	$0.0625 / s
720p	$0.1250 / s
1080p	$0.2500 / s

More models by Alibaba

Price, resolution and duration show each model's full range.

Model	Type	Price	Resolution	Duration
Wan 2.2 Speech to Video	lipsync	$0.1250 – $0.2500 / s	480p – 720p	3 – 7 s
Qwen Image	image	$0.0250 / image	—	—
Qwen Image Max	image	$0.0938 / image	—	—
Qwen Image Layered	image	$0.0625 / image	—	—