Google made Gemini Omni 1.2 Flash generally available on 5 November 2026, across the Gemini API and Gemini for business. The video-generation and editing model now creates and edits clips natively up to 15 seconds long, up from 10 seconds in Omni 1.1, with durations selectable in one-second steps from 3 to 15 seconds — and Google cut the price 30% to about $0.07 per second for 720p video.

The upgrade is about control as much as length. Omni 1.2 Flash adds multi-turn conversational editing, so you can fix a clip with a follow-up message instead of starting over, and stronger reference following: up to six reference images for characters, products and style, plus motion clips and audio cues. Google's side-by-side evaluations give Omni 1.2 a 62% visual-consistency win rate against 38% for Omni 1.1 in text-to-video testing. Every video carries an imperceptible SynthID watermark.

Where you can use it depends on the product. Developers get the paid Gemini API (model ID gemini-omni-1.2-flash) and Google AI Studio; Flow gets 15-second clips, Extend and upscaling for Google AI plan subscribers; Vids offers 15-second clips at no additional cost with a Google account or Workspace subscription; and the Gemini app rolls 15-second videos out to Google AI Ultra subscribers. Omni 1.1 stays available during a four-week transition, with API requests automatically routing to 1.2 on 3 December 2026.

The price math is the quiet story. At $12 per million video-output tokens — 5,792 tokens per second of 720p — a full 15-second clip costs about $1.04 in video-output tokens, before input costs. That makes short AI video genuinely cheap for creators and marketers, and the general-availability status with enterprise SLAs and Provisioned Throughput means companies can now build production workflows on it. The catch for hobbyists: the model is not on the Gemini API free tier, so the cheapest route in is Vids or a Flow plan.

Sources