Google's Gemini Omni 1.2 Flash: 15-second AI video, 30% cheaper
Google's new video model makes and edits 15-second clips with sound for $0.07 a second at 720p. That's 30% less than Omni 1.1.

Gemini Omni 1.2 Flash now makes clips up to 15 seconds long, up from 10 seconds in Omni 1.1, and the price is down 30% to $0.07 per second at 720p. A full 15-second 720p clip costs about a dollar. Google released it on 5 November as generally available on the Gemini API, and developers can try it in AI Studio and the Google Cloud console.
The main new feature is multi-turn editing. You can keep changing a clip with follow-up prompts, such as swapping the product, changing the lighting or weather, or switching the aspect ratio, and it works on the whole 15 seconds. Generation can be guided with character, product or style images, motion clips up to three seconds long, and audio cues. Output includes synchronized sound and lip-synced dialogue. You can draft at 360p or 720p and upscale to 1080p or 4K. Every video carries an invisible SynthID watermark.
There are limits. The API has no free tier. Through the Gemini API, extended videos stop at 30 seconds in total. Editing uploaded video isn't available in the EEA, Switzerland or the UK. In DataCamp's own test, fast motion and physics still broke: a marble vanished and a bell rang late. The model is also coming to Google Vids, Flow, Google Ads and the Gemini app for AI Ultra subscribers.
Why it matters: at about $1 per 15-second clip that you can keep editing, AI video becomes cheap enough for ads and social content made in bulk.
Sources
Independent coverage
- Gemini Omni 1.2 Flash: 15-second video and lower pricing blog.google
- Gemini Omni 1.2 Flash: 15-Second Clips, Editing, and Pricing datacamp.com
Written by an AI pipeline from the sources above. Methodology · Report an error
The stories that matter for people who build with AI, with the source for every claim. Free, no spam.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.