Gemini Omni 1.2 Flash: 15s, 30% Cheaper
Google made Gemini Omni 1.2 Flash GA with native 15-second video and 30% lower pricing at $0.07/sec for 720p. Will creators draft cheaper social ads?
Hakkı ALKANPublished 3 min read
Google announced Gemini Omni 1.2 Flash on November 5, 2026. The model is generally available (GA) in Google AI Studio, the Gemini API, and Google Cloud.
Native clips stretch to 15 seconds, up from 10 seconds in Omni 1.1. Google also cut pricing 30%, to $0.07 per second for 720p video.
So what does that mean for you? For example, creators drafting ads, product explainers, or social spots can tell a fuller story in one generation. Then they can polish it in chat instead of starting over.
introducing gemini omni 1.2 flash, now available in ai studio and the gemini api
— Google AI Studio (@GoogleAIStudio) November 5, 2026
what's new:
- fast & 30% lower cost
- longer clips
- edit in conversation
- more natural speech
- more controllable shots
What is new in Gemini Omni 1.2 Flash?
According to Google's official blog, you can set duration from 3 to 15 seconds in one-second steps. Multi-turn conversational editing also lets you swap a product, background, lighting, weather, or aspect ratio without regenerating from scratch.
Reference adherence is stronger too. You can combine character, product, or style images with short motion clips (up to three seconds) and audio cues. As a result, faces, garments, packaging type, and brand colors hold better across camera angles.
Google also highlights more natural speech with clearer lip-sync and multi-speaker conditioning. Camera moves such as FPV flythroughs, zoom-outs, and orbits stay steadier with fewer jump cuts.
How does the draft-to-upscale workflow work?
Draft fast at 360p or 720p. Fix details with a follow-up edit. Then upscale the keepers to 1080p or 4K. That loop is how Google keeps costs down even before the 30% price cut.
Docs list the model id as gemini-omni-1.2-flash. Output carries an imperceptible SynthID watermark, and Provisioned Throughput is available for production traffic.
Google says Omni 1.1 Flash will route to 1.2 Flash on December 3, 2026. However, complex sports action, rapid script changes, and hard physics remain active development areas.
Where can you use it today?
Developers prototype in AI Studio and ship on the Gemini API. Businesses can use Google Cloud. Consumer and creator surfaces are rolling out in Flow, Google Vids (15-second clips at no additional cost with a Google account or Workspace), the Gemini app for Google AI Ultra subscribers, and Google Ads campaign tooling.
We previously covered Omni Flash 1.1 and Vids on Omni 1.1 Flash on ShiftDelete.Net. This 1.2 Flash launch is the GA step for longer, cheaper conversational video.
Editorial take: why 15 seconds matters
Ten seconds often truncates a product pitch. Fifteen seconds is closer to a complete social ad beat. Pair that with mid-conversation edits and the draft-upscale path, and iteration gets practical for small teams.
Google's edge is distribution: the same model shows up across API, Cloud, Vids, Flow, Ads, and the Gemini app. That matters more than a single benchmark slide.
Therefore creators who already draft in AI Studio should feel the price cut and longer native length first. Enterprise teams, meanwhile, get GA plus Provisioned Throughput on Google Cloud.
| Detail | Value |
|---|---|
| Announcement | November 5, 2026 |
| Model id | gemini-omni-1.2-flash |
| Native length | 3–15s in 1s steps (was 10s on 1.1) |
| 720p price | $0.07/sec (30% lower) |
| Editing | Multi-turn conversational editing |
| Resolution path | 360p/720p draft → 1080p/4K upscale |
| Availability | GA on Gemini API + Google Cloud; AI Studio |
| Safety / capacity | SynthID watermark; Provisioned Throughput |
Sources: Google blog, AI Studio model page, Gemini API Omni docs, Google AI Studio post on X.