Google launches Nano Banana 2 Lite and Gemini Omni Flash

Google has announced the release of Nano Banana 2 Lite and Gemini Omni Flash, targeting developers and creators focused on multimedia generation and editing. Nano Banana 2 Lite is now available via the Gemini API and is recommended for users of the earlier Nano Banana model. It is built for environments where speed and budget are priorities, generating images from text prompts in just four seconds and costing $0.034 per 1,000 images. The model handles prompt adherence, character consistency, and text rendering with high reliability, and can be swapped in for immediate performance improvements over its predecessor. Nano Banana 2 Lite is also being integrated into Google consumer platforms, including Search, the Gemini app, and Google Photos. > Introducing Nano Banana 2 Lite 🍌 and Gemini Omni Flash 🔮, our new generative media models in the Gemini API and AI Studio! > > Nano Banana 2 Lite is extremely fast (<4s image) & cheap ($0.034 / 1K image). > > Omni Flash is SOTA at video editing at $0.10 / sec, same as Veo 3.1 Fast! pic.twitter.com/qDxRpqpX5E > > — Logan Kilpatrick (@OfficialLoganK) June 30, 2026 Gemini Omni Flash is now accessible in a public preview via Google AI Studio and the Gemini API. It allows developers to generate and edit up to ten seconds of video using multimodal inputs, including text, images, and short video clips. Video editing is conversational and supports multimodal referencing, enabling creators to maintain scene consistency and synchronize text or graphics with video actions. The model is priced at $0.10 per second of video. Early feedback from industry partners highlights the model’s ability to support rapid creative workflows and its promise for building advanced digital experiences. Limitations at launch include a 10-second cap on generation, a lack of audio input support, and some scene-consistency challenges. > We’re shipping 2 major releases:⁰ > 🔘 Nano Banana 2 Lite: our fastest and cheapest Gemini Image model > 🔘 Gemini Omni Flash: now available via the Gemini API and in @GoogleAIStudio to help developers generate and edit high-quality videos. pic.twitter.com/fqB2sA5Xyl > > — Google DeepMind (@GoogleDeepMind) June 30, 2026 Both models use SynthID watermarking for content verification. Google continues to build out its generative AI ecosystem, aiming to provide secure, scalable tools for developers and end users across multiple platforms. Source