Gemini Omni 1.2 Flash
Released Nov 5, 2026
Google's third Omni video generation and editing model, raising one generation from 10 to 15 seconds and cutting the 720p price by about 30% against Omni 1.1 Flash.
- Price per second
- $0.070
- Max clip length
- 15 s
- Max resolution
- 4K
- Native audio
- Yes
- AA arena Elo
- —
- LMArena Elo
- —
- Capabilities
- text to video, image to video, video editing, extension
- Licence
- Proprietary
Strengths & weaknesses
Strengths
- Single generations and edits run 3 to 15 seconds, set in one-second steps
- About $0.07 per second at 720p, down from about $0.10 on Omni 1.1 Flash
- Multi-turn conversational editing that fixes a detail without regenerating the whole clip
- Native speech, music and effects with multi-speaker conditioning and tighter lip-sync
Weaknesses
- 1080p and 4K are upsampled, not native
- Google says fast sports action and complex physics are still weak
- No free tier on the Gemini API
Generally available on the Gemini API and Gemini for business (Google Cloud) from 2026-11-05 per Google's launch post, with Provisioned Throughput; also rolling out in Flow, Google Vids, the Gemini app (AI Ultra) and Google Ads. maxDurationSec is one generation (Google Cloud model page: 'Output video duration (generation and editing): 3 to 15 seconds'). Extension takes up to the last 10 seconds of input and adds 3 to 10 seconds, concatenated onto up to the last 30 seconds of the input. Up to 10 reference images and 3 reference videos (up to 3 seconds each) per prompt; first-and-last-frame generation supported; audio input is not supported on the Cloud page even though the launch post mentions audio cues. The Gemini API pricing page says requests to gemini-omni-1.1-flash are routed to 1.2 Flash and billed at 1.2 rates from 2026-12-03. Outputs carry SynthID and C2PA Content Credentials. Not yet on the Artificial Analysis or LMArena video boards as of 2026-11-09.
Links
API model strings
- google-gemini-api
gemini-omni-1.2-flash - google-vertex
gemini-omni-1.2-flash