Best AI Video Tools

Google's Gemini Omni 1.2 Flash makes 15-second clips and costs 30% less

Google's newest video model stretches single clips from 10 to 15 seconds, adds multi-turn editing and drops API pricing to $0.07 a second at 720p. It is rolling out to Flow, Vids and the Gemini app.

Google released Gemini Omni 1.2 Flash on 5 Nov and made it generally available in the Gemini API and Gemini for business, according to Google’s announcement.

The biggest change is length. Google says one generation can now run up to 15 seconds, up from 10 on Omni 1.1, and you can pick any length from 3 to 15 seconds. It also claims better reference following across character, product and style images, steadier faces and products from first to last frame, clearer lip-sync with several speakers, and fewer unwanted cuts in long camera moves. You can edit the same clip over several turns, for example swapping the background or the aspect ratio, instead of regenerating it.

Developers pay $0.07 a second for 720p, which Google says is 30% less than Omni 1.1. Drafts can run at 360p, and the best takes can be upscaled to 1080p or 4K.

For consumers, Google says the model is rolling out to Flow, to Google Vids (15-second clips at no extra cost), and to the Gemini app for AI Ultra subscribers first. Flow’s credit costs for 15-second clips aren’t published yet, so check them before planning a project around them.

Source: Google blog, 5 Nov 2026

Tools in this story

More AI video news