Google announced Gemini Omni 1.2 Flash on November 5, 2026, generally available across the Gemini API and Gemini for business. The announcement page carries a date without a time of day. Read the announcement.
What changed
- Longer clips: native generation and editing up to 15 seconds, up from 10 seconds in Omni 1.1, with duration selectable in one-second increments from 3 to 15 seconds.
- Price: 30% below Omni 1.1 — $0.07 per second for 720p video. The workflow also keeps costs down: draft at 360p or 720p, fix details with follow-up edits instead of regenerating, then upscale finished clips to 1080p or 4K.
- Multi-turn conversational editing: clips can be adjusted through follow-up turns without starting over.
- Reference adherence: generation can be guided with character, product or style images, motion clips up to three seconds, and audio cues; the announcement states faces, garments, packaging typography and brand colors stay consistent across camera angles.
- Consistency: stronger character, object and scene consistency from first to last frame with less drift or morphing, including keyframe interpolation and clip extension.
Who is affected
Video-generation users of the Gemini API, Google Cloud, Gemini for business and Google Vids. The announcement's consistency claims are illustrated with Google's own examples rather than independent evaluation.
For the model-family context see the September roundup (Omni 1.1 Flash in Flow, AI Studio and the Gemini app) and the Gemini profile; vendor-example caveats are explained in our verification guide.
