Google Cuts AI Video Generation Cost by 30% with New Gemini Omni 1.2 Flash Model

Google has launched Gemini Omni 1.2 Flash, an updated AI video generation model that can create 15-second videos and edit existing clips through conversational prompts. The model is now generally available through the Gemini API and Gemini for business, and Google has reduced the price by 30% compared to its predecessor.

The cost reduction means generating 720p videos now costs $0.07 per second, or about $1.05 for a full 15-second clip via the API. Google is also integrating the model into its consumer and enterprise products, including Google Vids, Flow, Google Ads, and the Gemini app.

Gemini Omni 1.2 Flash extends the maximum video duration from 10 to 15 seconds and improves video consistency, speech generation, and editing capabilities. Users can modify backgrounds, products, lighting, weather, or aspect ratios using follow-up prompts without regenerating the entire video.

The model also better preserves faces, clothing, product packaging, text, and colors during movement and camera transitions, according to Google. It can combine reference materials such as character photographs, product images, style references, short motion clips, and audio cues to create more detailed videos.

For instance, users can merge a model’s photograph with multiple clothing images to produce a virtual try-on video that showcases different outfits from various angles. In another demonstration, Google showed the model repeatedly changing a video’s background while maintaining the characters’ movements, clothing, and camera framing.

The launch reflects ongoing efforts to make AI video generation more accessible and cost-effective for businesses and creators, with potential applications in advertising, marketing, and content creation.