Hook, body and CTA from three video models in one 30-second Short
Seedance 2.5 for a 4 s hook, Wan 3.0 for a 20 s body and Omni Flash for a 6 s call to action cost $9.31 in generation, $9.41 with the Timeline join.

You can spend the expensive model only where the viewer is deciding to stay. A 30-second Short with a 4-second Seedance 2.5 hook at 1080p, a 20-second Wan 3.0 body at 720p and a 6-second Omni Flash call to action at 1080p costs $9.31 in generation and $9.41 after the $0.10 Timeline render.
The same 30 seconds as one Wan 3.0 720p job is $3.75; the mix pays about $5.56 extra for a sharper opening. All three models list 9:16, and Shorts are vertical (YouTube Help, read 2026-10-09).
The mix, line by line
Seedance 2.5 has a 4-second minimum, which is exactly a hook length. Wan 3.0 covers 2 to 30 seconds. Omni Flash 1.1 covers 3 to 10 seconds.
| Segment | Model | Seconds | Resolution | Rate per second | Cost |
|---|---|---|---|---|---|
| Hook | seedance-2.5 | 4 | 1080p | $1.42155 | $5.69 |
| Body | wan-3.0 | 20 | 720p | $0.125 | $2.50 |
| CTA | gemini-omni-flash-1.1 | 6 | 1080p | $0.1875 | $1.13 |
| Total | 30 | $9.31 |
Join with soft cuts
Request all three as 9:16 so the shapes match, import the outputs, then render one file. Timeline's fit defaults to cover, which fills the frame; the output defaults to 1080x1920 so the 720p body is scaled to the same canvas as the 1080p ends.
curl -X POST https://api.sume.com/v1/timeline-1.0/render \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: short-mixed-001" \
-d '{"audio":{"mode":"silence","duration_seconds":30},
"video":[
{"source_url":"https://media.sume.com/artifacts/artf_demo/clip1.mp4","start":0,"duration":4},
{"source_url":"https://media.sume.com/artifacts/artf_demo/clip2.mp4","start":4,"duration":20,"transition":{"type":"fade","duration":0.25}},
{"source_url":"https://media.sume.com/artifacts/artf_demo/clip3.mp4","start":24,"duration":6,"transition":{"type":"fade","duration":0.25}}],
"output":{"width":1080,"height":1920}}'Limits
- Different models render different looks; keep the style line and any reference image identical across all three prompts.
- Omni Flash takes no audio reference, while Seedance 2.5 and Wan 3.0 do; if one narration file must drive the clips, use it as the Timeline audio spine instead.
- A transition must be on slot 2 or later and no longer than half the shorter neighbor.
- Totals use list rates read 2026-10-09; confirm pricing_skus in GET /v1/videos/models.
Sources
Related posts
More in Use cases
- Museum exhibit intros on Wan 3.0: 22 s each, eight for $22.00 at 720p
A 22-second Wan 3.0 clip costs $1.375 at 480p, $2.75 at 720p and $5.50 at 1080p on Sume, the same as two 11-second jobs. One job keeps the shot continuous.
- Nano Banana 2.1 0.5K is a 512 tier; YouTube thumbnails need 640 wide
The Image API names its smallest tier 512, below YouTube's 640-pixel minimum thumbnail width. 91 test thumbnails cost $6.825 at 0.5K, $9.10 at 1K, $13.65 at 2K.
- 120 Nano Banana 2.1 2K hero images: $6.05 at Google, $18.00 on Sume
Google lists Nano Banana 2.1 at $0.0504 per 2K image; Sume lists $0.15. For 120 listing hero images that is $6.05 versus $18.00, plus what the difference buys.
- Nano Banana 2.1 product photo 1:1: 1024, 2048, 4096 and cost per tier
Square product shots with Nano Banana 2.1: 1024, 2048 and 4096 px sizes, what each costs on Sume, and what you cannot do, such as transparent output.
Written by Sume