Gemini Omni 1.2 Flash
gemini-omni-1.2-flash
Google · chat · api
Context
131.1K
Max output
65.5K
Input $/1M
$1.50
Output $/1M
$9.00
Modalities
text
Released
05 Nov 2026
AI summary
● machine-written
Google releases Gemini Omni 1.2 Flash video generation model
Gemini Omni 1.2 Flash is Google's multimodal video generation and editing model that creates clips up to 15 seconds long with native audio in multiple resolutions from 360p to 4K. The model supports text-to-video, image-to-video, interpolation, and multi-turn editing capabilities. Released to general availability on November 5, 2026, it features a 30% price reduction compared to its predecessor and improved visual consistency.
What's new
- Extended video generation from 10 seconds to 15 seconds per clip
- Multi-turn conversational editing and extension support via previous_job_id
- 30% price reduction to approximately $0.07 per second at 720p
- Improved reference management for subjects and video inputs
- 62% visual-consistency win rate over Gemini Omni 1.1 Flash
Best for
Social media advertisement creationProduct explainer videosVideo editing and revision workflowsProduction teams requiring native audio and multi-format output
Source: https://ai.google.dev/gemini-api/docs/models/gemini-omni-1.2-flash