Wan 3.0 2-second clips: the shortest video length and what it costs
Wan 3.0's floor is 2 seconds, shorter than the 4-second minimum on Seedance 2.x models. Send duration 2 to wan-3.0; at 720p it costs $0.25 before the agent fee.

The shortest Wan 3.0 clip is 2 seconds. Send duration: 2 to wan-3.0 on POST /v1/videos; durations are whole seconds from 2 to 30, and any other value is refused at submit. At 720p a 2 second clip is reserved at $0.25 in current pricing code, before the agent fee.
The 2 to 30 second range is on fal's Wan 3 page and in Sume's Video generation docs, read 2026-09-29. The docs give seedance-2.5 4 to 30 seconds, and most other catalog models at most 15.
What is a 2-second clip good for?
- A logo sting or an end card.
- A reaction cut or a single beat between two longer shots.
- A cheap test of a prompt before you pay for a longer take.
- Loops and micro-motion for a poster or a banner.
What does a 2-second clip cost?
Wan bills per second by resolution, so the clip cost is seconds times the rate.
| Resolution | 2 s clip |
|---|---|
| 480p | $0.13 |
| 720p | $0.25 |
| 1080p | $0.50 |
What happens with a duration of 1?
It is refused. The catalog lists only whole seconds from 2 to 30 for wan-3.0, and a value outside the list fails at submit with 400 unsupported_capability; the error's details.supported holds the list.
Should I use several 2-second clips instead of one long one?
Only if each shot is a different scene. Joined with POST /v1/timeline-1.0/render, short clips can make a fast cut; one continuous action belongs in a single longer take.
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