Omni Flash 40-second extension vs four 10-second Sume jobs: $5.00
Google describes Omni 1.1 Flash scene extension up to 40 seconds in 10-second steps. Sume lists 3 to 10 seconds per job, so 40 seconds is four jobs.

What Google describes
Google's Gemini Omni 1.1 Flash post (read 2026-10-05) lists scene extension that analyzes up to 10 seconds of prior context and extends up to 40 seconds in total, in 10-second steps, along with first and last frame control, a 360p draft mode, 720p standard and 1080p or 4K premium output, and video references of up to 3 seconds. It is available in AI Studio, the Gemini API, Google Flow and the Gemini app.
What Sume lists
Sume's catalog entry gemini-omni-flash-1.1 is 3 to 10 seconds per job at 360p, 720p, 1080p or 4K. Its capabilities are text-to-video, image-to-video with an optional end image, reference-to-video, and video-to-video edit (Video Router docs). The docs do not list a scene-extension capability, so a 40-second scene on Sume is a sequence of separate jobs that you plan yourself.
Each job bills the provider list times 1.25 per output second. Four 10-second jobs cost the following.
| Resolution | One 10 s job | Four jobs (40 s) |
|---|---|---|
| 360p | $0.375 | $1.50 |
| 720p | $1.25 | $5.00 |
| 1080p | $1.875 | $7.50 |
| 4K | $3.75 | $15.00 |
The difference that is not in the price
A native extension carries context from the earlier seconds. Four independent jobs do not. You can pass the final frame of one clip as image_url for the next, or use reference_video_urls with clips of up to 3 seconds each, but that is your pipeline, and Sume does not claim it equals native extension. Expect continuity to need review, and budget one retry in four.
Plan the run
- Draft the four beats at 360p first ($0.375 each), then re-render at the final tier.
- Use an
Idempotency-Keyper segment so a retry does not double-bill. - Join the segments with Timeline 1.0 at $0.10 per output minute, rounded up, per its docs.
A worked comparison
For a 40-second scene at 720p, four independent jobs are $5.00. If you draft each beat at 360p first, the drafts cost 4 x $0.375 = $1.50, so a draft-and-final pass is $6.50 at 720p. At 1080p the final is $7.50 and the whole pass is $9.00. These numbers are Sume's rows; Google's own extension pricing is not stated on the post I read.
If native extension is the reason you want Omni, check what is reachable through the catalog. Sume documents capabilities, and an extension mode is not among them.
The honest framing is that these are two different workflows with different costs and different continuity. Four independent jobs give you four separate takes that you join, and any continuity between them is yours to create. Native extension, as Google describes it, carries prior context forward; whether it is reachable through your integration depends on the surface you use, and I only quote the Sume side here.
If your story needs continuity, plan the cut points around what each job can deliver, test one join, and only then commit the budget for the whole scene.
Use the table of rates to set a ceiling before you start. A 40-second scene cannot cost more than 40 seconds times the rate of the tier you chose, plus any retakes. At 720p that ceiling is $5.00 for one pass, at 1080p $7.50 and at 4K $15.00, and you can multiply it by the number of takes you are willing to pay for. That turns an open-ended creative request into a bounded budget you can approve before submitting anything.
Keep the first scene small. Spend $0.375 on a 10-second 360p test of the opening beat, check framing and pacing, and only then queue the remaining beats.
Sources
Related posts
More in Comparisons
- Gemini Omni Flash 1.1 at $0.125 a second on Sume vs $0.10 at Google
Sume bills Omni Flash 1.1 at $0.125 per second at 720p. Google lists about $0.10. Here is the 25% gap in dollars for 100 holiday clips, and what it covers.
- Gemini TTS: 30 prebuilt voices or 150+? Which number to quote
Google's docs say 30 prebuilt voices; its changelog says 150+ prebuilt and custom. Quote the one that fits and compare with Sume voice-id selection.
- Two-voice dialogue: Gemini TTS vs ElevenLabs Text to Dialogue
Gemini TTS handles up to 2 speakers per request; ElevenLabs Text to Dialogue keeps continuity with surrounding text and request IDs. In Sume you stitch jobs.
- Voice Design from a text description: Gemini vs ElevenLabs
Gemini TTS has Voice Design and 200 custom voices per project; ElevenLabs lists Voice Design on v4. Sume's docs cover cloning, not voice design.
Written by Sume