Post-Cutoff

Google DeepMindGemini Omni familyCurrentVideo generationReleased 5 Nov 2026

Gemini Omni 1.2 Flash

Successor to Gemini Omni 1.1 Flash: longer clips, better reference adherence and lip-sync, fewer unwanted jump cuts, 30% cheaper.

Model idgemini-omni-1.2-flash

Price$0.07 per second of video

Checked6 November 2026

Where it stands

No newer video generation model in our registry yet.

All video generation models

Before it from Google
Gemini Omni Flash (Omni 1.1 Flash)May 2026
Weights
Closed weights; access is hosted only.

How to call it

3 ways to use Gemini Omni 1.2 Flash, with the model id each provider expects.

Providers, model ids, endpoints and docs for Gemini Omni 1.2 Flash
ProviderModel idEndpointDocs
Gemini API gemini-omni-1.2-flash blog.google
Google Cloud (Provisioned Throughput available) gemini-omni-1.2-flash
Web app gemini.google.com

Pricing

Prices for Gemini Omni 1.2 Flash
Per second of video$0.07

As published: “USD per second of 720p video (30% below Omni 1.1 Flash)”.

Source: blog.google, checked 6 November 2026.

Specs

Input
Text, images, audio and video
Output
Video and audio
Context window
Not published
Max output
Not published
Open weights
No
Licence
Proprietary
Released
5 November 2026
Status
Current
Type
Video generation

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • 15-second clips

    Native generation and editing of 3–15 s clips in one-second steps (Omni 1.1: up to 10 s); motion reference clips up to 3 s; draft at 360p/720p, upscale to 1080p or 4K.

    Source: blog.google

Notes

GA Nov 5, 2026 on the Gemini API and Google Cloud; also Google Vids, Gemini app (AI Ultra), Flow, Google Ads. Not yet on independent video arenas (checked 2026-11-06).

Not yet checked against an official source: Endpoint presumably the same Interactions API as Omni 1.1 (not verified).