AI News
All stories
Official

Google releases Gemini Omni 1.2 Flash with cheaper, longer video clips

Gemini Omni 1.2 Flash is generally available in the Gemini API, with 3 to 15 second clips, conversational editing and a 30% lower price.

Products · · Updated · 1 min read

Watch the short

Under a minute, read by an AI anchor. Made . The story has been updated since, and the text below is the current version.

YouTube loads only when you press play.

Pricing is $0.07 per second at 720p, which Google puts 30% below Omni 1.1. The model generates native clips of 3 to 15 seconds.

The model's main claimed improvements concern consistency across a clip. Google says Omni 1.2 Flash better follows reference images, keeps subjects stable over time, handles multiple speakers and lip-sync, and produces continuous camera motion. It also supports multi-turn conversational editing, which means a user can refine a generated clip through successive text instructions. Draft, edit and upscale workflows reach 1080p and 4K, while the base generation price is quoted at 720p.

The announcement's limits matter as much as its gains. Google still flags weaknesses in fast sports and action, in rapid script changes, and in complex physics simulation.

What changed

Gemini Omni 1.2 Flash is generally available in the Gemini API, generating 3 to 15 second clips at $0.07 per second at 720p, which Google says is 30% below Omni 1.1.

Type: New capability · Applies to: Gemini Omni 1.2 Flash, Gemini API, Gemini Omni 1.1

Why it matters

Lower per-second pricing and longer native clips make AI video generation more practical for production workflows such as ads and product clips, though Google's own limitations matter for action-heavy content.

What you can do

Teams producing video could test the model on their own clip types and price it against current video workflows.

How the story developed

  1. The changelog adds that paid-tier rate limits doubled and that Gemini Omni 1.1 Flash requests route to 1.2 Flash from December 3, 2026.

  2. Adds the $12.00 per 1M token output price, doubled paid-tier rate limits, and the December 3, 2026 automatic routing of gemini-omni-1.1-flash requests to 1.2 Flash.

Original source

Where we saw it

2 sources

Gemini API changelog, Latent Space

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it. How it works