Google DeepMind announced Gemini Omni 1.2 Flash on 5 November 2026, extending its video-generation model’s native clips to 15 seconds from the 10 seconds supported by Omni 1.1. The company says the new model is generally available through the Gemini API and Gemini for business.
Google DeepMind has set the price at $0.07 per second for 720p video, which it says is 30% lower than for Omni 1.1. Users can choose a duration from 3 to 15 seconds in one-second increments. According to the company, a follow-up prompt can change details such as a clip’s background or lighting across its full length without generating it again. Drafts can be made at 360p or 720p, then upscaled to 1080p or 4K.
Making a product explainer could begin with a lower-resolution draft, continue with a requested change to the same clip and finish with an upscaled version, if that editing sequence works as Google DeepMind describes.
Google DeepMind says the release is backed by Google Cloud’s infrastructure, offers Provisioned Throughput and places an imperceptible SynthID watermark on outputs.
