Gemini Omni 1.2 Flash: What's New Compared With 1.1

Gemini Omni 1.2 Flash adds 15-second clips, multi-turn editing and a 30% lower API price. Here is what changed from 1.1 and what to test first.

V

Veo3 AI Team · 3 min read · Nov 6, 2026

Gemini Omni 1.2 Flash: What's New Compared With 1.1

Google released Gemini Omni 1.2 Flash on November 5, 2026. The short version: clips can now run to 15 seconds, the API price is 30% lower, and you can edit the same clip over several turns instead of starting again.

Everything below comes from Google's announcement and the Gemini API documentation. We have not run our own benchmark yet.

Gemini Omni 1.2 Flash vs 1.1 at a glance

Omni 1.1 Flash Omni 1.2 Flash
Maximum native clip 10 seconds 15 seconds
Duration control Fixed lengths on many tools 1-second steps from 3 to 15 seconds
API price at 720p About $0.10 per second $0.07 per second
Status Being phased out of the API Generally available

Google says the price fell 30% from 1.1. The 1.1 figure above is worked out from that cut.

What actually changed

Longer clips

Fifteen seconds is enough for a full social ad or a short product explainer in one generation. You also set the length in one-second steps, so you no longer have to round to a preset.

Multi-turn editing

You can change a background, swap a product, adjust the lighting or switch the aspect ratio on the same clip. Google says this works across a full 15-second video. It matters most when you need several variants of one idea.

Closer reference following

You can combine character, product and style images, motion clips of up to three seconds and audio cues. Google says faces, garments, packaging type and brand colors hold steadier across camera angles.

Better speech and camera moves

Dialogue, lip sync and multi-speaker scenes are improved. Google also reports fewer unwanted jump cuts in long camera moves such as FPV flights and zoom-outs.

What it still struggles with

Google names fast sports action, rapid script changes and complex physics as areas still in development. If your idea depends on those, test before you commit.

What happens to Omni 1.1?

According to the Gemini API docs, gemini-omni-1.1-flash stays available for a four-week transition. From December 3, 2026, API requests to it route automatically to 1.2 and are billed at the lower rate. That applies to Google's API. Third-party tools may move on their own schedule.

How to try it

Google lists the Gemini API, Google AI Studio, Google Cloud, Flow, Google Vids, Google Ads and the Gemini app, where 15-second video is rolling out to Google AI Ultra subscribers. Availability can vary by product, plan and region.

Using Omni on Veo3 AI

Veo3 AI is an independent product, not Google. Today our Omni model is 1.1 Flash, with clips of up to 10 seconds, and we have not added 1.2 yet. Until we do, 15-second clips are not available here. If your project fits in 10 seconds, you can use 1.1 in your browser with no Google subscription, and the credit cost is shown before you generate.

FAQ

When was Gemini Omni 1.2 Flash released?

Google announced it on November 5, 2026.

Is Gemini Omni 1.2 Flash better than 1.1?

On paper, yes: longer clips, lower API pricing and better consistency. Run your own prompt on both if your output has to match existing work.

What is the maximum length of Gemini Omni 1.2 Flash?

15 seconds natively, with lengths from 3 to 15 seconds in one-second steps.

Does Gemini Omni 1.2 Flash have a watermark?

Google says outputs carry an imperceptible SynthID watermark.

Ready to create AI videos?
Turn ideas and images into finished videos with the core Veo3 AI tools.

Related Articles

Continue with more blog posts in the same locale.

Browse all posts