Google launches Nano Banana 2 Lite for fast AI images and Gemini Omni Flash for video via API

Google adds two new generative AI models. Nano Banana 2 Lite generates images in four seconds at $0.034 a pop.

Gemini Omni Flash opens up video generation and editing via text prompts through the API for the first time. Nano Banana 2 Lite generates images in four seconds Google says Nano Banana 2 Lite is built for fast ideation and high-throughput developer pipelines. Text-to-image generation takes four seconds and costs just $0.034 per image at 1K resolution. The new image model goes by gemini-3.1-flash-lite-image in the API. Despite the speed focus, Google says Nano Banana 2 Lite still delivers reliable prompt following, consistent character rendering, and readable text in generated images. Beyond developer platforms, the model is rolling out across Google’s consumer products too, including AI Mode in Google Search, the Gemini app, NotebookLM, Google Photos, Stitch, Google Flow, and Google Ads.Ad Nano Banana 2 Lite brings the Nano Banana family to three production models. Google positions Nano Banana 2 (Gemini 3.1 Flash Image) as the all-rounder with the best balance of quality and cost. Nano Banana Pro (Gemini 3(.1) Pro Image) targets complex, professional use cases and offers what Google calls the strongest control and most advanced reasoning. AdDEC_D_Incontent-1 Comparison table of the Nano Banana model family. | Image: GoogleDevelopers can pick the right model based on whether they need speed, quality, or low cost. Google considers the original Nano Banana (Gemini 2.5 Flash Image) outdated. We still mostly use Nano Banana Pro ourselves, since its image quality and prompt reliability tend to beat both Nano Banana 2 and OpenAI’s GPT-Image-2. Gemini Omni Flash brings video generation to the API Gemini Omni Flash was first shown at Google I/O and is now available to developers through the Gemini API and Google AI Studio. The model combines Gemini’s multimodal reasoning with video generation and editing. Pricing is $0.10 per second of video output, matching Veo 3.1 Fast.Ad Google says the model’s strengths are conversational video editing through natural language, the ability to mix input formats like text, images, and video, and tapping into Gemini’s world knowledge for generation. Text and graphics can sync directly with video actions.