Does Wan 3.0 allow 2-second clips for a Shorts cold open?
Yes. Wan 3.0 on Sume accepts 2 to 30 seconds per call, so a 2-second cold open at 720p is $0.25, and it is the cheapest hook test in a season.

Yes. The Videos docs list wan-3.0 at 2 to 30 seconds, so a 2-second cold open is a valid request. At 720p, $0.125 per second, it costs $0.25.
Seedance 2.5 starts at 4 seconds and Omni Flash 1.1 at 3, so Wan is the one that can generate a two-second hook as its own clip.
Why test hooks as separate clips
A series lives or dies on the first seconds of each episode, and a hook is cheap to vary. Generating six two-second openings and one body is six times $0.25 for the openings. You pick one and join it to the body in Timeline.
YouTube's Help page on Shorts series describes a series as a Shorts-only playlist with seasons and episodes, with each episode at most 180 seconds (read 2026-10-07). The cold open is yours to design inside that limit.
| Model | Shortest call | 720p rate |
|---|---|---|
| wan-3.0 | 2 s | $0.125/s |
| gemini-omni-flash-1.1 | 3 s | $0.125/s |
| seedance-2.5 | 4 s | See pricing page |
A batch of openings
Eight two-second Wan openings at 720p cost $2.00. At 480p they cost $1.00. Use 480p to choose, then re-run the winner at 720p. Send resolution; Wan's estimator treats a missing one as 1080p.
Pair this with the 180-second episode post for the body, and keep the chosen opening's prompt so the next episode can reuse its style.
The hook is not the episode
Two seconds is a hook, not a story. Put the visual hook in frame one; if the shot needs to build, ask for 4 seconds and cut it in the edit with video trim, which costs $0.02 per job.
Use the eight clips as variants of one opening beat: same character and setting, a different first action. Join the chosen one to the body in the Timeline render.
Sources
Related posts
More in Models
- MiniMax H3 open weights: what is released and what stays API-only
MiniMax opened H3-Base on 2026-08-03 with two checkpoints, but 2K regeneration and Context-IR stay API-only. How that maps to Sume's minimax-h3 rows.
- Where can you use Gemini 3.8 Flash TTS today? API, Notebook, Vids
Google lists Gemini 3.8 TTS in the Gemini API, AI Studio, Gemini Notebook and Google Vids now; the Enterprise API is coming soon. What Sume offers instead.
- Which Sume image models are text-to-image only, with no photo edits
Five Sume image models reject reference images: Higgsfield Soul, Imagen 4 Fast, Imagen 4 Ultra, Recraft V4 and Qwen Image Max. Prices, ratios and edit options.
- Which Sume video clips carry audio for the Shorts editor split
YouTube Shorts now separates audio and video tracks. Which Sume video models return sound, which can mute, and what a $0.01 detach adds.
Written by Sume