Release dates
— Google made Gemini Omni 1.2 Flash (`gemini-omni-1.2-flash`) generally available in the Gemini API and Google Cloud on 2026-11-05, with video generation up to 15 seconds and multi-turn conversational editing. ↗
Gemini Omni 1.2 Flash
The general-release model in Gemini Omni’s video generation and conversational editing line, with native generation up to 15 seconds, multi-turn editing, and stronger multi-reference consistency.
Gemini API model ID `gemini-omni-1.2-flash`, generally available in the Gemini API and Google Cloud; consumer-product access is rolling out in phases. Google separately announced that the old ID `gemini-omni-1.1-flash` will auto-route to 1.2 starting 2026-12-03; that change is not yet effective.
MODEL NUMBER254
- First public date
- 2026-11-05
- Organization
- Google DeepMind
- Family
- Gemini Omni
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
Gemini Omni 1.2 Flash is a distinct API model and formal successor in the existing video family. It extends native clips from 10 seconds in 1.1 to 15 seconds and adds multi-turn video editing; no open weights or undisclosed parameter counts are inferred.
PreviousGemini Omni 1.1 Flash— · — ctx
CurrentGemini Omni 1.2 Flash— · — ctx
04
Architecture & capabilities
Model capabilities
Video generationVideo editingConversational editingVideo extensionMulti-referenceCharacter consistency
05
Release history
Google made Gemini Omni 1.2 Flash (`gemini-omni-1.2-flash`) generally available in the Gemini API and Google Cloud on 2026-11-05, with video generation up to 15 seconds and multi-turn conversational editing.
View source06
Related models
Select a card to view the related model.
07
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.