Omni Flash 1.1 extends to 40 s: what Sume offers instead
Google says Omni Flash 1.1 extends in 10 s steps to 40 s. Sume lists Omni at 3-10 s, no extend. Four clips cost $5.00 at 720p; H3 Max needs three.

Google's Omni 1.1 Flash announcement describes scene extension that reads up to 10 seconds of prior context and reaches 40 seconds in total, in 10-second steps. Sume's Video Router lists gemini-omni-flash-1.1 at 3 to 10 seconds and does not expose extend, so a 40-second video on Sume is a set of separate clips.
The cheapest way to cover 40 seconds with native audio on Sume is minimax-h3-max at 768p: three clips for $4.00. Four Omni clips at 720p cost $5.00.
What Google says
The Google post (read 2026-10-05) says Omni 1.1 Flash analyzes up to 10 seconds of prior context, extends in 10-second steps up to 40 seconds, supports first and last frame control, and adds a 360p draft mode that is up to 60 percent faster at a third of the cost of standard 720p. It lists 720p standard and 1080p or 4K premium, and video references of up to 3 seconds. It is available in AI Studio, the Gemini API, Google Flow and the Gemini app.
The earlier Omni Flash release, per Google Cloud (read 2026-10-05), made 3 to 10 second clips at 720p with up to 7 image references and up to 3 clips of no more than 3 seconds.
What Sume exposes
The Sume docs list gemini-omni-flash-1.1 at 360p, 720p, 1080p and 4K for 3 to 10 seconds, in 16:9 or 9:16, with native synced audio always on. They also state that the API does not expose previous_interaction_id or extend, because it is not in the published input schema of the provider. Edit mode with a video_url is a Video Router field.
| Plan | Clips | Per second | Total |
|---|---|---|---|
| Omni 1.1 Flash 720p | 4 x 10 s | $0.125 | $5.00 |
| Omni 1.1 Flash 1080p | 4 x 10 s | $0.1875 | $7.52 ($1.88 each) |
| H3 Max 768p | 15 + 15 + 10 s | $0.10 | $4.00 |
| H3 Max 1080p | 15 + 15 + 10 s | $0.20 | $8.00 |
| Wan 3.0 720p | one 30 s + one 10 s | $0.125 | $5.00 |
The practical difference
An extension-aware model carries a scene forward from what it just generated. Separate clips do not. On Sume you can pin the first frame of the next clip to the last frame of the previous one on rows that take start/end frames, which keeps the subject but not the motion or the sound. Plan cut points rather than expecting a seamless 40-second take.
If you need Omni's 4K, it is $0.375 per second on Sume, so a 10-second 4K clip is $3.75. The 360p draft tier lists at $0.03 per second, $0.0375 billed, which makes a 10-second draft $0.38.
- Want more than 10 s from Omni on Sume: stitch clips.
- Want fewer joins: H3 Max (15 s) or Wan 3.0 (30 s).
- Need audio continuity: replace the sound on a timeline.
A plan for a 40-second spot
Break the spot into four beats of 10 seconds each. Render the beats at Omni's 360p draft tier first, at $0.38 each, which is $1.52 for all four. Promote the beats that work to 720p at $1.25 each, or 1080p at $1.88 each. That gives a four-beat spot for $5.00 at 720p, plus the drafts.
If the beats do not need Omni's edit mode, three H3 Max clips are $4.00 at 768p and carry native stereo audio, but each clip is a fresh generation with its own sound. In both cases, join on a timeline and put one music bed under the whole spot.
Keeping the beats consistent
Whatever route you take, continuity is your job. Reuse the same reference images in every beat, repeat the wardrobe and setting words in each prompt, and end each beat on a frame you would be happy to start the next from. Check the beats side by side at 360p or 480p before you pay for the final tier.
Sources
Related posts
More in Comparisons
- 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.
- 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.
Written by Sume