Google releases Gemini Omni 1.2 Flash: 15-second videos and 30% cheaper

Google DeepMind has moved the Gemini Omni 1.2 Flash video generation and editing model to GA status, extending clips to 15 seconds and reducing the price by 30% to $0.07 per second of 720p.

Compiled by Sergey KostenchukPublished 2026-11-05Updated 2026-11-05

2026-11-05 Research Google

🤖 Google releases Gemini Omni 1.2 Flash: 15-second videos and 30% cheaper

Google DeepMind has made the video model generally available: clips up to 15 seconds (previously 10) with 1-second increments, priced at $0.07 per second of 720p. It claims background, lighting, and angle edits via dialogue, reference following, and lip-sync for multiple speakers.

🌍 Cheaper and longer — video generation pays off in mass scenarios: catalogs, ad spots, CTV. Adobe Firefly, Runway, Picsart, and others are already integrating the model, while SynthID and Provisioned Throughput address enterprise needs.

👤 A 720p draft → dialogue-based edits → upscale to 4K reduces iteration costs. Test in Google AI Studio and Gemini API; generate in Google Vids and Flow.

Source 1: https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/ Source 2: https://cloud.google.com/blog/products/ai-machine-learning/gemini-omni-1-2-flash-generally-available

Sources