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 provide developers with faster and more cost-efficient tools for creating multimedia content. Nano Banana 2 Lite is designed for high-speed image generation, offering text-to-image outputs in four seconds at a cost of $0.034 per 1,000 images. It is intended to replace the legacy Nano Banana model, providing better performance for rapid prototyping and high-volume workflows.

Gemini Omni Flash is now available for developers to create and edit videos using natural language, text, images, and video inputs. Priced at $0.10 per second of video output, the model supports conversational video editing and multimodal referencing. While it currently supports 10-second video generations, it allows users to synchronize text and graphics with video actions, drawing on Gemini’s underlying knowledge of narrative logic and real-world concepts.

These models are accessible through Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform. By chaining these tools together, developers can build end-to-end experiences, such as generating an image with Nano Banana 2 Lite and animating it into a video with Omni Flash. Both models incorporate SynthID watermarking to ensure content transparency and are built on Google’s secure infrastructure.