On June 30, 2026, Google launched two new generative media models for developers. Nano Banana 2 Lite (model ID gemini-3.1-flash-lite-image) is the fastest and most cost-efficient model in the Nano Banana image family, delivering text-to-image outputs in about 4 seconds at 0.034 dollars per image at 1K resolution while maintaining prompt adherence, character consistency, and legible text rendering. Google positions it as the recommended replacement for the original Nano Banana (gemini-2.5-flash-image).
The second model, Gemini Omni Flash (gemini-omni-flash-preview), entered public preview as a natively multimodal video model. It combines text, image, and video inputs for video generation and conversational editing, currently supports 10-second video generation with text-action synchronization, and is priced at 0.10 dollars per second of video output.
Both models are available in Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform; Nano Banana 2 Lite is also rolling out across consumer surfaces including AI Mode in Search and the Gemini app, while Omni Flash reaches the Gemini app and Google Flow. The pairing shows Google segmenting generative media by cost tier: cheap, high-throughput drafting models alongside richer multimodal video workflows, aimed at developers who scale image and video generation inside products.