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

Google DeepMind has announced the release of two new AI models: Nano Banana 2 Lite and Gemini Omni Flash. Nano Banana 2 Lite is the fastest and most cost-effective image generation model in the Nano Banana family, capable of producing an image from a text description in 4 seconds at a cost of $0.034 per 1,000 images. It is designed for scenarios where speed and low cost are critical, and is recommended as a replacement for the previous Nano Banana model (gemini-2.5-flash-image). The model is already available in Google AI Studio, Gemini API, Gemini Enterprise Agent Platform, as well as on Google consumer surfaces such as AI Mode in Search, the Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads. Meanwhile, Gemini Omni Flash is a model for generating and editing video from text, images, and video, introduced at Google I/O. It supports dialog-based video editing, multimodal references, and text-to-action synchronization. The price is $0.10 per second of video, matching the price of Veo 3.1 Fast. Limitations include generating videos of up to 10 seconds, lack of support for audio references and scene extension in the API, as well as limitations on character consistency across scene changes. Both models use SynthID watermarks for safety. Developers can combine the models to build complex multimedia applications, for example, generating an image in Nano Banana 2 Lite and then animating it into a video using Gemini Omni Flash.