Wan 3.0 30-second video: one clip, no stitching
Wan 3.0 makes a single clip of up to 30 seconds with audio. Set duration to 30 on wan-3.0 in POST /v1/videos. Here is the request, the cost, and the limits.

Wan 3.0 can generate a clip of up to 30 seconds in one call. On Sume, send model: "wan-3.0" and duration: 30 to POST /v1/videos; any whole number of seconds from 2 to 30 is accepted, and audio comes from the same pass unless you turn it off.
Both vendor pages read 2026-09-29 give the range: fal's Wan 3 page says 2 to 30 seconds in a single generation, and Alibaba Cloud's guide says 2 to 30 seconds. Sume's catalog matches, per its Video generation docs.
How do I request 30 seconds?
Give the scene a shape that can fill the time: a start, a change, an end.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: wan-30s-001" \
-d '{
"model": "wan-3.0",
"prompt": "A hiker starts at a trailhead at dawn, climbs through pine forest, then reaches a ridge as the sun clears the clouds",
"duration": 30,
"resolution": "720p",
"aspect_ratio": "16:9"
}'How much does a 30-second Wan 3.0 clip cost?
The amount is reserved on submit, at the provider list price × 1.25, before the agent fee.
| Resolution | Reserved for 30 s |
|---|---|
| 480p | $1.88 |
| 720p | $3.75 |
| 1080p | $7.50 |
How long does it take?
The docs say video generation typically takes 30 seconds to several minutes depending on model and parameters. Poll the job about every 30 seconds, or pass a callback_url and let Sume notify you; the job is completed when unsigned_urls has the download.
What if I need more than 30 seconds?
Chain clips. Generate scene by scene, pulling a still from near the end of one clip with POST /v1/video-frames (at[]) to use as the first_frame of the next, then join them with POST /v1/timeline-1.0/render. The 30 seconds is one generation, not a limit on the video you can make.
Sources
Related posts
More in Models
- Wan 3.0 document to video: what the model reads and what Sume passes
Alibaba's Wan 3.0 can read an uploaded document to make a video. On Sume's video API today wan-3.0 takes prompts, frames and media references, not a file input.
- Wan 3.0 first and last frame: animate between two images
Wan 3.0 can make a clip that starts on one image and ends on another. On Sume, send frame_images with first_frame and last_frame to wan-3.0; last needs first.
- Wan 3.0 omni reference video: images, clips and audio in one prompt
Omni reference means one request carries mixed references. Wan 3.0 takes up to 10 images, 5 videos and 5 audio tracks; on Sume, send them as input_references.
- Wan 3.0 reference limits: how many images, videos and audio clips
Wan 3.0 reference-to-video takes up to 10 images, 5 video clips and 5 audio tracks. See the per-type caps, what Sume rejects with unsupported_capability, why.
Written by Sume