How long can a video from Gemini Omni 1.1 Flash be?

Gemini Omni 1.1 Flash extends a clip in 10-second increments up to a cumulative length of 40 seconds. Each extension analyzes up to 10 seconds of the preceding footage, which is what keeps the visuals consistent across the joins rather than letting the scene drift on every new segment.

How much cheaper is the 360p draft mode?

The 360p draft mode in Gemini Omni 1.1 Flash generates up to 60% faster and costs one third of the standard 720p output, according to Google. Drafts are meant for iterating on a shot before committing, so a creator can throw away ten bad takes for roughly the price of three finished ones.

Where can developers access Gemini Omni 1.1 Flash?

Gemini Omni 1.1 Flash is available in Google AI Studio and through the Gemini Enterprise Agent Platform API. Google Flow exposes it to AI Plus, Pro and Ultra subscribers, and the scene extension feature also appears in the Gemini app. Developer documentation for the model lives at ai.google.dev/gemini-api/docs/omni.

Can Gemini Omni 1.1 Flash use an existing video as a reference?

Yes. Gemini Omni 1.1 Flash accepts up to three seconds of video as multimodal context, alongside text and image inputs. Combined with first and last frame control — where you supply a start frame and an end frame and the model fills the motion between them — that gives directors a way to pin down transitions and camera moves.

Google · 2026-08-27 · major

Gemini Omni 1.1 Flash — Google's video model gets keyframes and 4K output

Gemini Omni 1.1 Flash is Google's production video generation model, now with scene extension to 40 seconds, start and end keyframe control, a cheap 360p draft mode and 4K upscaling.

Google hero graphic for the Gemini Omni 1.1 Flash video generation model

Google's video model now takes direction: fixed keyframes, 40-second scenes, cheap 360p drafts and 4K finals.

Quick facts

Maker	Google
Model id	gemini-omni-1.1-flash
Max clip length	40 seconds, in 10-second extensions
Prior context read	Up to 10 seconds
Draft mode	360p, up to 60% faster, one third the cost of 720p
Output resolution	1080p or 4K upscaling
Availability	Google AI Studio, Gemini Enterprise Agent Platform API, Google Flow, Gemini app

What is it?

Scene extension is the headline change in Gemini Omni 1.1 Flash, Google's production video generation model announced on August 27, 2026. A clip grows in 10-second steps to a total of 40 seconds, and each step reads up to 10 seconds of what came before. Google frames the release as creative control for developers rather than raw quality gains.

How does it work?

Four other controls sit alongside the extension. First and last frame specification makes the model generate the motion between two supplied keyframes. A 360p draft mode renders previews up to 60% faster at a third of the 720p cost. A 4K upscaling path produces 1080p or 4K finals. And the model accepts up to three seconds of video as reference context, on top of text and images.

Why does it matter?

Generative video has been hard to use in real production because output was a lottery — you prompt, you wait, you pay, you get something close but wrong. Cheap 360p drafts move the expensive render to the end of the loop instead of the middle, and keyframe control turns a prompt into a brief with fixed endpoints. Both are workflow fixes, not model-quality claims.

Who is it for?

developers and video teams building on the Gemini API

Frequently asked questions

How long can a video from Gemini Omni 1.1 Flash be?: Gemini Omni 1.1 Flash extends a clip in 10-second increments up to a cumulative length of 40 seconds. Each extension analyzes up to 10 seconds of the preceding footage, which is what keeps the visuals consistent across the joins rather than letting the scene drift on every new segment.
How much cheaper is the 360p draft mode?: The 360p draft mode in Gemini Omni 1.1 Flash generates up to 60% faster and costs one third of the standard 720p output, according to Google. Drafts are meant for iterating on a shot before committing, so a creator can throw away ten bad takes for roughly the price of three finished ones.
Where can developers access Gemini Omni 1.1 Flash?: Gemini Omni 1.1 Flash is available in Google AI Studio and through the Gemini Enterprise Agent Platform API. Google Flow exposes it to AI Plus, Pro and Ultra subscribers, and the scene extension feature also appears in the Gemini app. Developer documentation for the model lives at ai.google.dev/gemini-api/docs/omni.
Can Gemini Omni 1.1 Flash use an existing video as a reference?: Yes. Gemini Omni 1.1 Flash accepts up to three seconds of video as multimodal context, alongside text and image inputs. Combined with first and last frame control — where you supply a start frame and an end frame and the model fills the motion between them — that gives directors a way to pin down transitions and camera moves.

Try it

Call model id gemini-omni-1.1-flash in Google AI Studio