Gemini Omni 1.2 Flash (GA)

Google made Gemini Omni 1.2 Flash generally available in the Gemini API on November 5, 2026, for video generation and conversational editing.

Lab
Google DeepMind
Release date
Status
Generally available
API model ID
gemini-omni-1.2-flash
Context window
131,072 tokens
Max output
65,536 tokens

The Gemini API changelog lists Gemini Omni 1.2 Flash (gemini-omni-1.2-flash) as generally available on November 5, 2026, with video generation and conversational editing of up to 15 seconds, first-and-last-frame interpolation and per-turn extension of 3 to 10 seconds up to 30 seconds in total, and better character and subject consistency across up to six reference images. The model page lists text, image and video input, video with native audio and text output, an input limit of 131,072 tokens and an output limit of 65,536 tokens. The same changelog entry says requests to gemini-omni-1.1-flash will route to this model from December 3, 2026.

Modalities
Text, image and video input; video with native audio, and text output
Availability
Gemini API. Requests to gemini-omni-1.1-flash route to this model from December 3, 2026.
Official source
ai.google.dev
Last checked

Questions

When did Gemini Omni 1.2 Flash become generally available?
November 5, 2026.
How long can Gemini Omni 1.2 Flash videos be?
Up to 15 seconds per generation, and up to 30 seconds in total with per-turn extension, per Google.
What happens to Gemini Omni 1.1 Flash?
From December 3, 2026, requests to gemini-omni-1.1-flash route automatically to gemini-omni-1.2-flash.

Source

Release dates, model IDs and limits come from each lab’s own announcement, changelog, documentation or deprecations page, linked on every model with the date it was last checked. How we pick and check sources: editorial standards.

The Model Press

What are you looking for?

Search by headline, topic or keyword.