Gemini Omni 1.2 Flash
Google·
Overview
Successor to Gemini Omni 1.1 Flash (2026-08-27) for video generation and editing, generally available on Google Cloud since 2026-11-06 as the model id gemini-omni-1.2-flash. Clips run up to 15 seconds, up from 10 in 1.1, with conversational multi-turn editing of the same clip and native audio including dialogue, lip-sync and multi-speaker conditioning. Drafts render at 360p or 720p and are upscaled to 1080p or 4K. Text, image and video references are generally available; audio references are gated behind allowlisting. API price at 720p is $0.07 per second, which Google states is 30% below Omni 1.1 Flash, with similar reductions at other resolutions. Live via the Gemini API, the Google Cloud console and Google Vids, with Provisioned Throughput; Gemini for business is announced as coming soon. Outputs carry a SynthID watermark. Google publishes no benchmark figures for the model.
Capabilities and innovations
Benchmarks
No tracked academic benchmark applies to video models; the timeline carries no scores and no leadership tracking for them.
- GPQA Diamond: not reported by the vendor
- Humanity’s Last Exam (no tools): not reported by the vendor
- SWE-bench Verified: not reported by the vendor
- SWE-bench Pro: not reported by the vendor
- MMLU: not reported by the vendor
- MMLU-Pro: not reported by the vendor
- Terminal-Bench 2.x: not reported by the vendor
- MMMU-Pro: not reported by the vendor
Links
More from Google
Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.