Start building with Nano Banana 2 Lite and Gemini Omni Flash

Google has released two new generative AI models, Nano Banana 2 Lite and Gemini Omni Flash, to help developers create and scale multimedia experiences. Nano Banana 2 Lite is the fastest and most cost-efficient image model in the Nano Banana family, designed for high-volume workflows and rapid prototyping. It delivers text-to-image outputs in four seconds at a cost of $0.034 per 1,000 images, making it a practical replacement for the legacy Nano Banana model.

Gemini Omni Flash is now available for developers to use for high-quality video generation and conversational editing. This model allows users to refine videos using natural language and supports multimodal inputs, such as combining text, images, and video to maintain scene consistency. It is currently priced at $0.10 per second of video output and is available in public preview through Google AI Studio and the Gemini API.

These models are designed to work together, allowing developers to chain rapid image generation with video animation. By using Nano Banana 2 Lite to create images and passing them to Gemini Omni Flash, creators can build end-to-end workflows that transform static visuals into cinematic clips. Both models include SynthID watermarking to support content transparency and are built on Google’s secure infrastructure.