Gemini Omni Flash 1.1 stretches clips to 40 seconds
Google's video model now extends clips in ten-second steps, upscales output to 4K and adds a cheaper, faster 360p preview mode.
A darkened editing room with glowing monitors and empty timelines — an AI-generated illustration.
Version 1.1 of Gemini Omni Flash extends clips in ten-second steps to a total of 40 seconds, generates transitions between a given start and end frame, and upscales results to as much as 4K.
At a glance
- Scene extension now reads 10 seconds of preceding footage as context, up from 1 second.
- Clips grow in 10-second increments to a maximum total length of 40 seconds.
- Google says 360p previews render 60 percent faster and cost a third less than the 720p standard.
- Up to 3 seconds of outside video can be attached as visual reference material.
- Available via the Gemini API in Google AI Studio, the Enterprise Agent Platform API and Google Flow.
Google shipped version 1.1 of Gemini Omni Flash on August 28, 2026. The release is an editing update rather than a new base model: longer scenes, transitions between two fixed frames, and an upscaling path that tops out at 4K.
Ten seconds of context instead of one
When the model extends a shot, it now reads 10 seconds of the preceding footage as context. The previous version looked at a single second. Extensions run in 10-second increments up to a total clip length of 40 seconds, which is where Google draws the line.
A second editing mode fills the gap between a supplied start frame and end frame. Google points to camera pans, zooms and seamless loops as the intended use. Creators can also attach up to three seconds of reference video as visual context.
The cheap preview matters more than the 4K
The headline feature is 4K upscaling, but the 360p preview is the part that changes day-to-day work. Google says those previews render 60 percent faster and cost a third less than the 720p standard. That ratio decides how many variants a team can afford to generate and then throw away.
What the announcement does not address is how much genuine detail the upscaler recovers at 4K, as opposed to simply cleaning up edges.
Where it runs
Access comes through the Gemini API in Google AI Studio and through the Gemini Enterprise Agent Platform API. In Google Flow, version 1.1 is open to Google AI Plus, Pro and Ultra subscribers worldwide.
Omni Flash was introduced in May at the Google I/O developer conference. It is presented as an orchestration layer over existing building blocks rather than a standalone video foundation model. Seedance 2.0 and Kling 3.0 are named as its competition.
What we could not verify
Only one independent newsroom stands behind this report. We could not confirm per-second pricing, any benchmark result against Seedance 2.0 or Kling 3.0, or whether the 40-second ceiling also applies to 4K output. The speed and cost figures for the 360p preview are Google's own numbers and were not independently measured here.
FAQ
How long can a Gemini Omni Flash 1.1 video be?
Up to 40 seconds. Extensions are applied in ten-second increments, and each step uses ten seconds of the preceding footage as context.
Is the 360p preview cheaper than normal rendering?
Google puts it at a third less than the 720p standard and 60 percent faster. Those figures come from Google and were not independently measured.
Where can I use Gemini Omni Flash 1.1?
Through the Gemini API in Google AI Studio, the Gemini Enterprise Agent Platform API, and in Google Flow for AI Plus, Pro and Ultra subscribers.
