Google DeepMind Launches Nano Banana 2 Lite and Gemini Omni Flash Models

Google DeepMind has launched two new models: Nano Banana 2 Lite, which delivers text-to-image outputs in 4 seconds at a cost of $0.034 per 1K images, and Gemini Omni Flash, designed for video generation at $0.10 per second. Both models became available on June 30, 2026, through platforms such as Google AI Studio, Gemini API, and Gemini Enterprise Agent Platform, as stated by Product Manager Alisa Fortin. Gemini Omni Flash supports 10-second video generations and accepts video references up to 3 seconds long, with plans for longer durations in the future. This release follows the introduction of Gemini Omni Flash at Google I/O. Practitioners can now leverage these models to enhance their applications, particularly in areas like Google Photos and Google Ads, where integration is facilitated through the Gemini app and Google Flow. For further details, visit the Google DeepMind Blog.