Google launches Gemini Omni Flash video model and Nano Banana 2 Lite for developers

Google launched two generative media models for developers on June 30, 2026, leading with Gemini Omni Flash, a video model that generates and edits clips up to 10 seconds long through its API at $0.10 per second of output. The second release, Nano Banana 2 Lite, is the company’s fastest and cheapest Gemini image model, Google said.

The through-line is cost, not capability. Both models trade peak quality for price and speed, aimed at developers building media features at scale rather than chasing benchmark wins. Nano Banana 2 Lite generates images in about four seconds at $0.034 per 1K image at 1K resolution, and Google says it delivers roughly 60% to 70% of the broader Nano Banana 2 line’s general capability at a fraction of the cost.

Gemini Omni Flash accepts text, image and video inputs and supports conversational editing, letting developers refine a clip through natural-language instructions. It is available in public preview through Google AI Studio, the Gemini API, the Gemini app and Google Flow.

Nano Banana 2 Lite reaches developers via Google AI Studio, the Gemini API and the Gemini Enterprise Agent Platform, and is rolling out to AI Mode in Search, the Gemini app, NotebookLM and Google Photos, Google Cloud said.

The video model carries real limits Google disclosed at launch: audio references are not yet supported, video references up to three seconds are accepted but not fully processed, and character consistency degrades during scene transitions. The 60% to 70% capability figure for the image model is Google’s own and has not been independently tested.