Gemini Omni 1.1 Flash: 40-second scenes, 360p drafts
The update stretches scenes to 40 seconds, adds first- and last-frame control, and prices a 360p draft mode at $0.03 per second.
Illustration: a darkened editing suite where abstract timelines and keyframe markers glow across curved monitors.
Gemini Omni 1.1 Flash hands developers more control over generated video: scenes extend in 10-second steps up to a total of 40 seconds, and a 360p draft mode costs $0.03 per second.
At a glance
- Price per second: 360p $0.03, 720p $0.10, 1080p $0.15, 4K $0.30.
- Scene extension works in 10-second steps up to a 40-second total length.
- The model reads up to 10 seconds of the existing clip, against only the last second before.
- Google puts the 360p draft mode at up to 60 percent faster and one third the cost of 720p.
- Available through Google AI Studio; reference clips of up to three seconds are supported.
Google shipped Gemini Omni 1.1 Flash on August 27, 2026, an update to its video generation model that competes on control rather than on picture quality. The new features aim at the part of the job that eats studio time: making one shot continue the way the last one ended. Pricing pushes in the same direction, with a cheap tier for the takes nobody keeps.
Draft first, pay for resolution later
The headline addition is a 360p mode built for previews. Google puts it at up to 60 percent faster and one third the cost of 720p. When a take finally works, it can be upscaled to 1080p or 4K.
The ordering is the point. Expensive seconds are spent only on shots that already hold together, which matters more to a team running twenty variations of a scene than any incremental gain in fidelity.
Scene extension reads more of the past
Clips grow in 10-second steps to a total of 40 seconds. The model now examines up to 10 seconds of the footage it has already produced, where the previous behavior considered only the final second. Google credits that wider window for steadier continuity across successive extensions.
Two more controls come from ordinary post-production practice. Supplying a first and a last frame makes the model generate the movement in between, which turns camera moves into something a director can specify. Separately, up to three seconds of a user's own video can act as a reference so characters and visual style hold across shots.
Price per second
| Resolution | Price per second |
|---|---|
| 360p | $0.03 |
| 720p | $0.10 |
| 1080p | $0.15 |
| 4K | $0.30 |
The same price list sets the model against the earlier Gemini Omni Flash as well as Veo 3.1 Lite and Veo 3.1 Fast. The Decoder reads the table as showing the new version undercutting them at the lower resolutions.
Where developers can reach it
Access runs through Google AI Studio and the developer documentation. Enterprises get it via the Gemini Enterprise Agent Platform API. Google Flow opens the model to AI Plus, Pro and Ultra subscribers worldwide, while the Gemini app starts with scene extension for Plus, Pro and Ultra customers.
What the sources do not settle
The speed and cost figures are Google's own, and no independent measurement was available at publication. Whether the per-second price covers an audio track, and which aspect ratios the model supports, is not stated in the material reviewed here. Neither source compares output quality directly against Veo 3.1.
FAQ
How much does Gemini Omni 1.1 Flash cost?
Billing is per second of generated video: $0.03 at 360p, $0.10 at 720p, $0.15 at 1080p and $0.30 at 4K.
How long can a Gemini Omni 1.1 Flash video be?
A scene can be extended in 10-second steps to a total of 40 seconds, with the model taking up to 10 seconds of the existing footage into account.
Where can I use Gemini Omni 1.1 Flash?
In Google AI Studio and through the developer documentation, via the Gemini Enterprise Agent Platform API for enterprises, and in Google Flow for AI Plus, Pro and Ultra subscribers.
