39 vertical Omni Flash clips of 7 s: $34.13 at 720p, $51.19 at 1080p
39 clips of 7 seconds on Gemini Omni Flash 1.1 is 273 seconds: $10.24 at 360p, $34.13 at 720p, $51.19 at 1080p and $102.38 at 4K on Sume, with native audio.

Thirty-nine 9:16 clips of 7 seconds each on Gemini Omni Flash 1.1 add up to 273 output seconds, which costs $34.125 at 720p, $51.1875 at 1080p, $10.2375 at 360p and $102.375 at 4K on Sume. Native audio is always on for this model, so there is no separate audio line to add.
Seven seconds sits inside the model's 3-10 second window, and both 16:9 and 9:16 are supported, so a vertical batch needs no cropping step.
The price table
Each figure is rate x 273 seconds. Rates are Sume's, as of 2026-10-09.
| Resolution | USD per second | One 7 s clip | 39 clips |
|---|---|---|---|
| 360p | $0.0375 | $0.2625 | $10.2375 |
| 720p | $0.125 | $0.8750 | $34.1250 |
| 1080p | $0.1875 | $1.3125 | $51.1875 |
| 4K | $0.375 | $2.6250 | $102.3750 |
Submitting 39 jobs
Thirty-nine accepted jobs is more than Pro's 24 and under Startup's 48. On Pro, submit 24, wait for completions, then submit the other 15. In the meantime the balance has to hold 24 x $0.875 = $21.00 at 720p.
If you submit on Free, only six are accepted at a time, so the 39 clips take seven submit rounds. Keep one idempotency key per clip and persist the job id on submit: a replay with the same key returns the original job instead of a second paid one.
Picking the resolution
For vertical social clips viewed on a phone, 720p is the first resolution worth pricing: the step from 720p to 1080p adds 50 percent ($0.0625 per second) and the step to 4K triples the 720p cost. A 360p batch is useful as a review pass. At $10.24 for the whole batch it lets you drop weak prompts before the 720p run, which costs about three times as much.
As with other video models, resolution is the only lever once the duration is fixed. If your edit needs 8-second clips, multiply by 8 instead of 7: 39 x 8 x $0.125 = $39.00 at 720p.
Budget checkpoints
Three checkpoints keep a 39-clip run honest. Before submit, compute the full batch at your chosen resolution. After the first wave, compare debited_usd_micros with the expected figure for the clips that completed. After the last wave, confirm final is true and no hold remains. If a clip fails, the hold is refunded and you can regenerate it, but a clip you simply dislike is already captured. For a 39-clip batch at 720p, set aside a regeneration reserve of about 25 percent, which is $8.53.
Why seconds, not clips, set the price
The price is per output second, so 39 clips of 7 seconds cost the same as 21 clips of 13 seconds, both 273 seconds. That makes trimming a prompt's requested duration the cheapest edit available: asking for 6 seconds instead of 7 across the batch saves 39 x $0.125 = $4.875 at 720p. The model accepts 3 to 10 seconds, so check that your edit really needs the last second before paying for it.
Sources
Related posts
More in Pricing
- A $4.44 ceiling per clip at 1080p or 4K: which Sume models still run
Under a $4.44 cap per clip, Wan 3.0 1080p runs 17 s and H3 Max 1080p its full 15 s, but Seedance 2.5 1080p cannot start. Table of the longest clip per row.
- 4-second 1080p clip: Veo 3.1 Fast $0.48 at Google vs Sume
Google lists Veo 3.1 Fast at $0.12/s for 1080p, so 4 s is $0.48. Sume's cheapest 4 s 1080p-class row is Gemini Omni Flash 1.1 at $0.75.
- 4-second 1080p clip: Veo 3.1 $1.60 at Google vs Sume
Google lists Veo 3.1 at $0.40/s for 1080p, so 4 s is $1.60. Sume's cheapest 4 s 1080p-class row is Gemini Omni Flash 1.1 at $0.75.
- 4-second 1080p clip: Veo 3.1 Lite $0.32 at Google vs Sume
Google lists Veo 3.1 Lite at $0.08/s for 1080p, so 4 s is $0.32. Sume's cheapest 4 s 1080p-class row is Gemini Omni Flash 1.1 at $0.75.
Written by Sume