Gemini Omni 1.2 Flash: 15-Second Video, Editing, Pricing and Access

What Gemini Omni 1.2 Flash is

Gemini Omni 1.2 Flash is a video generation and editing model from Google DeepMind, released and made generally available on 5 November 2026 across the Gemini API and Gemini for business. Google lists four main changes from Gemini Omni 1.1: native clips of up to 15 seconds, multi-turn conversational editing, closer following of reference images, and a price 30% lower. Google also states that, for the first time, Gemini Omni is generally available with Google Cloud's enterprise infrastructure, that Provisioned Throughput is offered, and that every output carries an imperceptible SynthID watermark. On LMArena's video leaderboard Gemini Omni 1.2 Flash has 1540 Elo (rank 1).

Length, resolution and references

Clips can be set in one-second steps from 3 to 15 seconds, up from a 10-second limit on Omni 1.1. Google describes a workflow of drafting at 360p or 720p, fixing details with a follow-up edit rather than generating the whole clip again, and upscaling the chosen result to 1080p or 4K. Generation can be guided by character, product or style images, short motion clips of up to three seconds, and audio cues, and Google states that faces, clothing, packaging text and brand colours hold steady across camera angles. It also supports interpolating between a first and a last keyframe and extending a clip into a longer sequence.

Editing, speech and camera movement

Multi-turn editing lets a clip be changed turn by turn, for example swapping a product or background, changing the lighting or weather, or switching the aspect ratio, and it works across full 15-second clips. Google reports more natural dialogue, clearer lip-sync and separate conditioning for several speakers, and fewer unwanted jump cuts during continuous camera moves such as drone-style flythroughs, zoom-outs and orbits. Google names fast sports action, rapid script changes and complex physics as areas where development is still ongoing.

Pricing

Google's announcement gives the price as $0.07 per second of 720p video, 30% less than Gemini Omni 1.1. On the Gemini API the model is billed by tokens, at $1.50 per million input tokens and $12 per million video output tokens, which Google equates to about $0.07 a second at 720p. The cost of a clip therefore depends on its length and resolution; the price table on this page lists the figures with their source.

Where to use it

Developers can use the model through the Gemini API and prototype in Google AI Studio; businesses through the Google Cloud console. In Google's own apps it appears in Flow for directing scenes and multi-turn edits, in Google Vids for 15-second clips at no extra cost with a Google account or Workspace subscription, in the Gemini app for Google AI Ultra subscribers as it rolls out, and in Google Ads for video campaigns. Google's announcement also names Adobe Firefly, Figma Weave and Magnific among the products using it.

Official Resources