Gemini Omni Flash 1.1: what a 10-second 4K clip costs on Sume
A 10-second 4K Gemini Omni Flash 1.1 clip costs $3.75 on Sume; at 1080p it is $1.875 and at 360p $0.375. 3 to 10 seconds, 16:9 or 9:16, audio always on.

A 10-second Gemini Omni Flash 1.1 clip at 4K costs $3.75 through Sume: $0.30 per second provider list, times 1.25, times 10 seconds. The same clip is $1.875 at 1080p, $1.25 at 720p and $0.375 at 360p. Ten seconds is the longest the model accepts.
The Sume catalog id is gemini-omni-flash-1.1. It accepts 3 to 10 seconds in 16:9 or 9:16, at 360p, 720p, 1080p or 4K, with native synced audio that is always on. All values are as of 2026-10-08.
| Resolution | Provider list per second | Sume per second | 3 s | 8 s | 10 s |
|---|---|---|---|---|---|
| 360p | $0.03 | $0.0375 | $0.1125 | $0.30 | $0.375 |
| 720p | $0.10 | $0.125 | $0.375 | $1.00 | $1.25 |
| 1080p | $0.15 | $0.1875 | $0.5625 | $1.50 | $1.875 |
| 4K | $0.30 | $0.375 | $1.125 | $3.00 | $3.75 |
What the vendor says
The fal page for the text-to-video endpoint describes Gemini Omni Flash 1.1 as Google's multimodal video model that generates video with synchronized native audio from a text prompt, grounded in Gemini's real-world knowledge and physics understanding (fal page, read 2026-10-08). Google's Gemini API video page lists Gemini Omni Flash as a fast, multimodal model for video generation and conversational video editing (Google page, read 2026-10-08).
Default and the 4K token
If you send no resolution, the catalog default is 720p, and the default duration is 8 seconds: 8 x $0.125 = $1.00, which is the value Sume's own fixture reserves for a bare prompt. Send 4K in the catalog; the code accepts lowercase 4k as an alias and sends the right string to the provider.
4K is exactly twice the 1080p rate and three times the 720p rate, so use it only for the final render. A cheap workflow drafts at 360p ($0.0375 per second) and then repeats the prompt at 1080p or 4K.
curl -X POST https://api.sume.com/v1/video-router/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: omni-4k-001" \
-d '{"model":"gemini-omni-flash-1.1","prompt":"A paper crane unfolds on a sunlit desk","resolution":"4K","duration":10,"aspect_ratio":"16:9","mode":"async"}'Budget examples
Ten 10-second clips at 4K cost 10 x $3.75 = $37.50. The same ten clips drafted at 360p cost 10 x $0.375 = $3.75, and finishing the three best at 4K adds 3 x $3.75 = $11.25, for a total of $15.00 instead of $37.50. Drafting low and finishing high is the cheapest way to use the 4K tier.
Because the reserve at submit is the provider list times 1.25, make sure your workspace balance covers the full 4K reserve for a 10-second clip, which is $3.75, before you start a batch.
Limits
- No
generate_audiotoggle: audio is always on and the API rejectsfalse. - Aspect ratio: 16:9 or 9:16 only.
- Prompt: up to 20,000 characters.
- No
bitrate_modeand no reference audio. - Cost is the provider list x 1.25 for each output second, as a function of the resolution.
Sources
Related posts
More in Pricing
- Gemini Omni Flash $17.50 per million tokens vs Sume per-second price
Google lists Gemini Omni Flash video at $17.50 per million tokens, about $0.10 a second at 720p. Thirty 8-second clips: $24.00 at that rate, $30.00 on Sume.
- Gemini Omni Flash 1.1 edit mode: the default reserve is 8 s, $1.00
Editing a clip with Gemini Omni Flash 1.1 on Sume reserves 8 seconds by default: $1.00 at 720p. Send a duration hint of 6 and the reserve drops to $0.75.
- generation_spend_cap_usd of 0, 120, 450, null or 600: which applies?
On a Format run 120 and 450 are used as given, null is the $500 platform maximum, and 0 or 600 returns a 400. Omitted means the Format's cap or $400.
- GLM-5.3 off-peak 50% points vs a Sume dollar spend cap
Z.ai meters GLM-5.3 in points with a 50% off-peak rate. Why a Sume dollar cap is a different meter, and how to schedule agent work.
Written by Sume