Gemini Omni Flash 1.1 at 4K vs 1080p for an 8-second product ad
An 8-second Gemini Omni Flash 1.1 clip costs $1.00 at 720p, $1.50 at 1080p and $3.00 at 4K on Sume. Audio is always on and the ratio is 16:9 or 9:16.

On Sume, an 8-second Gemini Omni Flash 1.1 clip costs $1.00 at 720p, $1.50 at 1080p and $3.00 at 4K, so 4K costs three times the 720p price. The model takes 3 to 10 seconds, 16:9 or 9:16, always has native audio, and has four resolutions: 360p, 720p, 1080p and 4K.
Price by resolution
Per-second figures are the provider list rate times the 1.25 Sume margin that the docs describe, as of 2026-10-08. Read capabilities from GET /v1/video-router/models before you bill a batch, because rates and envelopes can change.
| Resolution | Per second | 8 seconds | 100 SKUs |
|---|---|---|---|
| 360p | $0.0375 | $0.30 | $30.00 |
| 720p | $0.125 | $1.00 | $100.00 |
| 1080p | $0.1875 | $1.50 | $150.00 |
| 4K | $0.375 | $3.00 | $300.00 |
What is fixed
The Video Router docs state these points for the model.
- Duration: 3 to 10 seconds.
- Aspect ratio: 16:9 or 9:16 only, so no 1:1.
- Native synced audio is always on; generate_audio false is rejected.
- Edit mode takes a video_url; aspect_ratio and duration are not sent.
When 4K is worth it
4K helps if the ad will be cropped in post, for example a 16:9 master that you cut to 9:16 plus a hero crop. For a feed ad that is shown at phone size, 1080p is half the cost of 4K. A sensible test is a 4K hero, a 1080p cutdown set and 720p tests: for 100 SKUs, 720p is $100, 1080p is $150 and 4K is $300. Confirm the audio fits your ad before you scale, since you cannot turn it off.
Budgeting a campaign
A campaign of 40 hero clips at 8 seconds and 1080p is 40 x $1.50 = $60. The same set at 4K is $120. If you need both a 16:9 master and a 9:16 cutdown, note that the ratio is chosen at generation, so a second ratio is a second job; plan 2 x $1.50 = $3.00 per SKU at 1080p, rather than assuming a crop.
Do not rely on the model for silent footage, because audio is always generated and cannot be turned off. If you need silent plates, pick Wan 3.0 or Seedance, or strip the audio with the audio detach tool at $0.01.
- 40 SKUs x 8 s x $0.1875 = $60.00 at 1080p.
- 40 SKUs x 8 s x $0.375 = $120.00 at 4K.
- Two ratios per SKU double the figure.
Before you scale
If a clip needs a longer take, remember the 10-second ceiling. A 15-second spot would be two Omni jobs joined in Timeline, with a cut between them, or a single job on a model that allows 15 seconds. The Timeline join of 16 seconds of output costs $0.10, so two 8-second 1080p clips and a join cost $3.10 in total.
You can test all three board jobs for under $4 at 720p. A 5 second text-to-video clip costs $0.625, a 5 second image-to-video clip $0.625 and a 5 second edit of a 5 second source $0.625. Three of each is 9 x $0.625 = $5.625.
Use GET /v1/video-router/models to read the live capabilities before you send, because the aspect ratios and lengths differ by mode. Remember that audio is always on, so a clip you want silent needs its audio removed afterwards.
Omni takes 3 to 10 second clips, 16:9 or 9:16 only. It cannot make a 1:1 clip, a clip over 10 seconds or a silent clip, since audio is always on. For those jobs use another id: Wan 3.0 or Seedance 2.5 for length, and see each model's capabilities for ratios.
The model also accepts reference images and videos, up to 10 images and 3 videos of at most 3 seconds each, so a short reference-led clip is possible on the same id.
Sources
Related posts
More in Models
- Gemini Omni Flash 1.1 on Sume: spec sheet and billing in one page
Everything that ships for gemini-omni-flash-1.1 on Sume: 3 to 10 seconds, four resolutions, two ratios, always-on audio, reference limits, edit mode, billing.
- Gemini Omni Flash 1.1 ranks 8th, 4th and 3rd on three AA boards
Gemini Omni Flash 1.1 is eighth on AA text-to-video, fourth on image-to-video and third on editing. On Sume it is one id at $0.125 a second at 720p.
- Gemini Omni rate limit: Google lists none, Sume lists them
Google's rate-limit page has no Omni or Veo row. It lists per-project RPM, TPM and RPD plus spend caps. Sume publishes per-key limits and concurrency by plan.
- GLM-5.3 reasoning cannot be turned off: cap the Sume run instead
Z.ai says GLM-5.3 always reasons, with low, high and max levels. What that means for run time and for a spend cap on a Sume agent run.
Written by Sume