Google's Gemini Omni 1.2 Flash goes fully available with 15-second video and a 30% price cut on 720p

Google DeepMind announced on November 5 that Gemini Omni 1.2 Flash, its AI video model, is now generally available. The model is live in the Gemini API and Gemini for Business, with native video generation and editing extended from 10 seconds to 15 seconds per clip, adjustable in one-second steps between 3 and 15 seconds. Pricing for 720p output falls 30% to $0.07 per second, or about $1.05 for a 15-second clip. (Image: official Google artwork.)

Multi-turn editing with reference images

The model supports multi-turn conversational editing, letting users refine a video in natural language across rounds, and accepts character, product and style reference images to keep the same character or product consistent across scenes. Output carries an invisible SynthID watermark identifying it as AI-generated. Google says the model improves on its predecessor in visual coherence and prompt adherence.

15 seconds first for Ultra subscribers; Flow and others follow

The 15-second capability inside the Gemini app will roll out first to Google AI Ultra subscribers; Flow, Google Vids and Google Ads are also getting the new model. Google has not said when free users will get 15-second generation.

(Source: Google official blog, November 5, 2026.)