Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

Google DeepMind has released Gemini Omni 1.2 Flash, a video generation model announced on November 5, 2026, in a post by product manager Anish Nangia. The company says it is making the model generally available through the Gemini API and Gemini for business, the first time the Omni line has reached that status, with Google Cloud infrastructure and Provisioned Throughput behind it.

The headline changes are longer clips and lower prices. Videos can now run natively up to 15 seconds, compared with 10 seconds on Omni 1.1, and duration can be set in one-second steps from 3 to 15 seconds. Google says pricing falls 30 percent from the previous version, to $0.07 per second for 720p. It suggests drafting at 360p or 720p, fixing details through follow-up edits, then upscaling the best results to 1080p or 4K.

Google also claims better adherence to reference images, short motion clips and audio cues, with faces, clothing, packaging text and brand colors holding steady across camera angles. Other promised improvements include multi-turn conversational editing across full clips, more natural multi-speaker dialogue and lip-sync, and continuous camera moves with fewer unwanted jump cuts. Outputs carry an imperceptible SynthID watermark.

The model is also rolling out in Flow, Google Vids, Google Ads and the Gemini app, where 15-second videos are going to AI Ultra subscribers first. Google acknowledges that fast sports action, rapid script changes and complex physics still need work. The release targets businesses and creators producing video at volume, where per-second cost and consistency matter most.