A $25 cap on Omni 4K: six 10-second clips and the leftover
With $25, Gemini Omni Flash 1.1 at 4K gives six 10-second clips ($22.50) and $2.50 left, enough for two more 3-second 4K clips. The reserve math on Sume.

With $25.00 you can make six 10-second clips of Gemini Omni Flash 1.1 at 4K on Sume, which costs $22.50, and the remaining $2.50 buys two 3-second 4K clips ($1.13 each) with 24 cents left. A 10-second 4K clip is 10 x 37.5 = 375 cents.
The count
Divide 2,500 cents by the clip price and round down. The table repeats it for four lengths.
Sume rounds each clip up to the next whole cent, so a clip total is ceil(seconds x rate), not a sum of fractional cents.
| Length | Per clip | Whole clips | Spent | Left |
|---|---|---|---|---|
| 3 s | 113 cents | 22 | $24.86 | $0.14 |
| 5 s | 188 cents | 13 | $24.44 | $0.56 |
| 8 s | 300 cents | 8 | $24.00 | $1.00 |
| 10 s | 375 cents | 6 | $22.50 | $2.50 |
The reserve at submit
The Video generation docs say Sume reserves the provider list times 1.25 at submit. A 10 s 4K job reserves $3.75, so with a balance of $3.74 the submit fails before any money moves. Submitting six at once reserves $22.50 of the $25.00 at the same time, and you can still submit two 3 s clips with the rest.
Treat the balance after the run, and the sum of usage.cost, as the numbers that count.
Cheaper ways to the same shot
If six hero shots are more than you need, make three 4K clips ($11.25) and nine 720p clips of 10 s ($11.25, at 125 cents each). That uses $22.50 for twelve clips. Or draft each shot at 360p for 38 cents, which is six drafts for $2.28, and spend the rest on the winners.
Whatever the plan, set a limit in your own code. The poll response gives usage.cost per job, so a loop can stop when the sum reaches $25.
The same length at every tier
For reference, a 10-second Omni Flash clip at each resolution. Every price is the seconds times the billable rate, rounded up to a whole cent, as of 2026-10-08.
| Resolution | Arithmetic | Billed |
|---|---|---|
| 360p | 10 x 3.75 = 37.5 cents | $0.38 |
| 720p | 10 x 12.5 = 125 cents | $1.25 |
| 1080p | 10 x 18.75 = 187.5 cents | $1.88 |
| 4K | 10 x 37.5 = 375 cents | $3.75 |
Limits to remember
These apply to every request on this page, from the Video Router and Video generation docs:
- Length is 3 to 10 whole seconds in generation modes; an edit takes no duration.
- Aspect ratio is 16:9 or 9:16; an edit takes no aspect ratio.
- Native synced audio is always on, and
generate_audio: falseis rejected. - There is no
bitrate_mode, no reference audio and noseed. - Billing is the provider list times 1.25 per output second, reserved at submit and shown in
usage.cost.
Sources
Related posts
More in Pricing
- Real estate listing voice-overs: 25 homes at 700 characters
25 listing narrations of 700 characters cost $0.385 on MAI-Voice-2.1, $0.263 on Flash, and $1.00 on Sume TTS as 25 jobs. See the batched figure.
- A 3-minute lip-sync reel on H3 Max: 13 chunks, $11.25 to $36.00
H3 Max lip-sync takes 5 to 14.8 seconds of audio per job. A 180 second track is 13 jobs: $11.25 at 480p, $18.00 at 768p or $36.00 at 1080p.
- 30, 60 and 90-second presenter videos: $5.52, $11.04, $16.56 Standard
On Sume, 30 s, 60 s and 90 s of avatar video cost $5.52, $11.04 and $16.56 at Standard, $7.35, $14.70 and $22.05 at Plus, $16.50, $33.00 and $49.50 at Max.
- 30 days of social images on GPT Image 2.5: 12 cents a day, $3.60
A month of one finished image per day, with 3 low drafts, 1 medium refine and 1 high final each day, costs 12 cents a day and $3.60 on Sume (GPT Image 2.5).
Written by Sume