Gemini Omni Flash 1.1
Released Aug 27, 2026
Google's updated Omni video generation and editing model, adding scene extension, first-and-last-frame control and 1080p/4K upscaled output to Gemini Omni Flash.
- Price per second
- $0.10
- Max clip length
- 10 s
- Max resolution
- 4K
- Native audio
- Yes
- AA arena Elo
- 1128
- LMArena Elo
- 1516
- Capabilities
- text to video, image to video, video editing, extension
- Licence
- Proprietary
Strengths & weaknesses
Strengths
- Scene extension in 10-second increments up to 40 seconds cumulative, using up to 10 seconds of prior context
- First-and-last-frame control for camera orbits, zoom transitions and seamless loops
- 360p draft mode renders up to 60% faster than 720p at about a third of the cost
- Text, image and video inputs with conversational video editing and native sound (speech, music, effects)
Weaknesses
- Single generation capped at 10 seconds
- 1080p and 4K are upscaled, not native
- No free tier on the Gemini API
maxDurationSec is one generation (Vertex model page: 10 s with or without audio); scene extension reaches 40 s cumulative per Google's launch post. Status is inconsistent across Google pages: the Gemini API models page lists it under 'Preview' with id gemini-omni-1.1-flash, the Vertex/Gemini Enterprise Agent Platform page lists launch stage 'Preview' with id gemini-omni-1.1-flash-preview, and the launch post calls it 'production-ready'. Resolutions 360p/720p/1080p/4K (Vertex page); 1080p and 4K via upscaling (launch post). Video references limited to 3 seconds. The Gemini API pricing page labels the entry 'Gemini Omni Flash' with id gemini-omni-1.1-flash. Leaderboard names: LMArena 'gemini-omni-1.1-flash' (#1, Sep 21 2026); Artificial Analysis 'Gemini Omni Flash 1.1' (#10, AA-Video-T2V v2.1 with audio, 2026-10-27).
Links
API model strings
- google-gemini-api
gemini-omni-1.1-flash - google-vertex
gemini-omni-1.1-flash-preview