Google made Gemini Omni 1.2 Flash, its AI video model, generally available. It makes 15-second clips, up from 10, lets users edit them over several chat turns and costs 30% less, at about $0.07 a second for 720p video.

Google has made Gemini Omni 1.2 Flash, the latest version of its AI video model, generally available and cut its price by 30%, the company said on Thursday. It now costs about $0.07 per second of 720p video through the Gemini API, down from $0.10 a second in June.

The model can now make clips up to 15 seconds long in one go, up from 10. Users can also edit a clip over several turns in chat, such as swapping a product or background or changing the lighting, instead of making it again from scratch. ByteDance’s Seedance 2.5, unveiled in June, makes 30-second clips.

Google says faces, clothes, packaging text and brand colours now stay more consistent across camera angles, with fewer glitches and jump cuts. In Google DeepMind’s own comparisons, testers preferred 1.2 over 1.1 for visual consistency 62% of the time.

The model is rolling out in Flow, Google Vids, Google Ads and, for Google AI Ultra subscribers, the Gemini app. Businesses can use it through Google Cloud, the first time Omni has been generally available there. Every video carries an invisible SynthID watermark.

Google first showed Omni Flash at its I/O conference in May, with clips capped at 10 seconds. It says it is still working on fast sports action, quick script changes and complex physics.

Google is the only US company with a model in the top 10 of one popular AI video ranking, where Chinese models hold the other nine spots.