Gemini Omni 1.2 Flash: 15-second video, price, how to try.

Gemini Omni 1.2 Flash is Google’s newest video generation and editing model, and the first Gemini Omni release that is generally available. Google announced it on 5 November 2026 with three headline changes: native clips up to 15 seconds, editing a clip through follow-up prompts instead of regenerating it, and a 30% lower price than Gemini Omni 1.1↗ (opens in a new tab). Here is what is new, what it costs, how to try it and what people are already making with Gemini Omni 1.2 Flash.

What is Gemini Omni 1.2 Flash?

Google’s AI Studio documentation describes Gemini Omni Flash as a high-performance model for fast, conversational video generation and editing. It turns text and images into video with native audio, lets you refine a generated video in natural language, and supports video extension, interpolation between a first and last frame, and output up to 4K. The API model code is gemini-omni-1.2-flash.

Google says the model is generally available on the Gemini API and Google Cloud, and that this is the first time Gemini Omni has been generally available, backed by Google Cloud’s enterprise infrastructure. Google Cloud’s model page lists the launch stage as GA with a release date of 5 November 2026. Outputs carry an imperceptible SynthID watermark, according to Google, and Cloud’s docs list Content Credentials (C2PA) support.

What’s new in Gemini Omni 1.2 Flash

Longer clips, up to 15 seconds

Clips can now run natively up to 15 seconds, up from 10 seconds with Omni 1.1. Google says you can set the duration in one-second steps from 3 to 15 seconds, which it pitches as enough room for a complete short story, a product explainer or a full social ad in one generation. First-and-last-frame interpolation is limited to 3 to 10 seconds, per the developer docs.

Editing in conversation

The biggest workflow change is multi-turn conversational editing. Google says you can refine the same clip turn by turn, for example swapping a product or background, changing the lighting or weather, or switching the aspect ratio, and that this works across full 15-second clips. Google’s own demo keeps two characters’ performances and camera framing intact while the background changes from a pavilion tent to a forest, a stable, a market fair and a castle.

Better reference adherence and consistency

You can guide a generation with character, product or style images, short motion clips of up to three seconds, and audio cues. Google says Omni 1.2 Flash holds faces, garments, packaging typography and brand colors steady across camera angles, with less drift or morphing between the first and last frame than Omni 1.1.

Speech and camera control

• More natural speech: Google says dialogue sounds more fluid, lip-sync is clearer and multiple speakers can be conditioned separately.
• Cinematic camera moves: Google says sweeping FPV flythroughs, zoom-outs and orbits come with significantly fewer unwanted jump cuts and steadier scale.
• Draft cheap, upscale later: you can draft at 360p or 720p, fix details with an edit, then upscale the best result to 1080p or 4K.

Google is also open about the limits: it says work is ongoing on fast sports action, rapid script changes and complex physics.

Gemini Omni 1.2 Flash pricing

Google’s headline number is $0.07 per second of 720p video, 30% less than Omni 1.1. On the Gemini Developer API pricing page, the paid tier costs $1.50 per million input tokens (text, image or video) and $9.00 per million text output tokens or $12.00 per million video output tokens. Video is billed at 5,792 tokens per second of 720p, which Google works out to about $0.70 for a 10-second clip and about $1.04 for a 15-second clip.

• 360p: about $0.023 per second
• 720p: about $0.07 per second
• 1080p with upsampling: about $0.104 per second
• 4K with upsampling: about $0.209 per second

There is no free tier for the model in the Gemini API. Google also says that from 3 December 2026, all API requests to gemini-omni-1.1-flash will automatically route to gemini-omni-1.2-flash and be billed at the new rates.

Who it’s for

Google positions Gemini Omni 1.2 Flash for businesses, developers and creators producing video at scale. Its examples lean commercial: virtual try-on clips from a model photo and product shots, catalog spins, branded ads and ad variants for different audiences, plus science explainers and multi-character animated scenes. The longer clips and edit-in-place workflow matter most if you make many variants of the same video.

How to try Gemini Omni 1.2 Flash

1. Developers: prototype in Google AI Studio and call the model through the Gemini API’s Interactions API with the model code gemini-omni-1.2-flash (paid tier).
2. Businesses: try it in the Google Cloud console; Google Cloud lists Provisioned Throughput and pay-as-you-go options.
3. Google apps: Google says you can direct scenes and multi-turn edits in Flow, generate 15-second clips at no extra cost in Google Vids, create 15-second videos in the Gemini app (rolling out to Google AI Ultra subscribers) and scale video campaigns in Google Ads.

Per Google Cloud’s documentation, the model supports 16:9 and 9:16 aspect ratios, up to 10 images per prompt, and editing input videos up to 15 seconds long.

What people are building with it

Creators have already started posting Omni 1.2 Flash clips. One early example on The Model Atlas is a wildlife-documentary clip made from a single Omni 1.2 prompt, where the creator calls out the animal motion and sound effects. You can browse every build made with the model on its model page, and compare it with other Google video work under Gemini.

Gemini Omni 1.2 Flash FAQ