Google Gemini Omni 1.2 Flash Is Live: 15-Second AI Video at 30% Lower Cost
Google’s AI video model just got longer, cheaper, and production-ready. Gemini Omni 1.2 Flash, announced on November 5, 2026, is now generally available across the Gemini API and Gemini for business — and for the first time, the Omni line is a full product, not a preview.
Two numbers matter most: clips now run up to 15 seconds, and the price dropped 30%. Here’s what that means if you make videos with AI.
15-Second Clips, Priced at $0.07 a Second
The biggest change is length. Gemini Omni 1.2 Flash generates and edits native video clips of up to 15 seconds, up from 10 seconds in version 1.1. You can pick the length second by second, from 3 to 15 seconds, so a short product shot costs less than a full scene.
The price fell with it. At 720p, generation now costs $0.07 per second — 30% less than Omni 1.1. A full 15-second clip at 720p runs about $1.05. Google says similar savings apply at other resolutions, though it has only published the 720p per-second rate so far.
Talk to Your Video to Edit It
The second big change is editing. Omni 1.2 Flash supports multi-turn conversational editing, which means you can change a video by describing what you want in plain words, then refine it again in the next message. Change the lighting, swap an object, adjust the mood — each round builds on the last instead of starting over.
Google also says the model follows reference images, video, and audio more closely than before, so characters and scenes stay consistent across clips. That’s the part creators usually complain about with AI video, so if it holds up in real use, it matters more than the price cut.
Where You Can Use It
Omni 1.2 Flash is rolling out across Google’s products and developer platforms. Developers can call it through the Gemini API in Google AI Studio, and businesses can use it in Vertex AI on Google Cloud, with Provisioned Throughput for teams that need reserved capacity. Outputs carry an imperceptible SynthID watermark, so AI-made video can be identified later.
For everyday users, it’s showing up in Flow, Google Vids, and the Gemini app. Google Vids users can create up to three 15-second videos a month at no cost with a Google or Workspace account. In the Gemini app, 15-second generation is rolling out to Google AI Ultra subscribers first.
What It Still Can’t Do Well
Google is open about the limits. Fast sports action, rapid scene changes, and complex physics are still weak spots, and the company says work there is ongoing. The consistency claims come from Google’s own demos too — no independent lab has published hands-on results yet. If you plan to use it for client work, test it on your own footage before promising results.
That said, the direction is clear. AI video is moving from short, expensive clips toward longer, cheaper, editable ones — and a production-ready model with public pricing means anyone can test it against their own workload today.
This is the same week OpenAI shipped its own big model news — read our report on GPT-6 Cyber, the security AI that found 948 Linux flaws, for the other side of the AI race.
The Bottom Line
Gemini Omni 1.2 Flash gives creators 15-second clips, conversational editing, and a 30% price cut — at $0.07 a second for 720p. It’s generally available now, backed by Google Cloud, and free to try in small amounts through Google Vids. If you’ve been waiting for AI video to get cheap enough for everyday use, this is the version to test.
Sources: Google Blog — Gemini Omni 1.2 Flash · Google Cloud Blog — Gemini Omni 1.2 Flash now GA
New to AI video tools? Our data recovery guide is a good reminder to back up your projects first — AI experiments are no excuse for losing your original files.