Start building with Nano Banana 2 Lite and Gemini Omni Flash

June 30, 2026 | Source: Google DeepMind Blog

Tags: Nano Banana, Gemini, Google DeepMind, image generation, video generation, Gemini API, multimodal

Google released Nano Banana 2 Lite (gemini-3.1-flash-lite-image), a 4-second, $0.034/1K-image model for high-throughput pipelines, alongside Gemini Omni Flash — now accessible to developers via the Gemini API for video generation and multi-turn conversational editing.

Details

Google DeepMind made two generative media models available to developers on June 30, 2026. Nano Banana 2 Lite (API ID: gemini-3.1-flash-lite-image) is the fastest and cheapest image model in the Nano Banana family, delivering text-to-image outputs in 4 seconds at $0.034 per 1,000 images. It is positioned as a direct replacement for Nano Banana 1 (gemini-2.5-flash-image), offering better speed, quality, and cost. The model targets high-volume production workflows, interactive prototyping, and rapid visual iteration.\n\nSeparately, Gemini Omni Flash — Google's cost-efficient video generation and conversational editing model — is now available in Google AI Studio, the Gemini API, and the Enterprise Agent Platform. Previously consumer-only (Gemini app and Google Flow), developers can now access it programmatically for the first time. Together, the two releases enable end-to-end multimedia pipelines: rapid image generation feeding into video creation and editing within a single developer workflow.\n\nBoth models roll out simultaneously to consumer surfaces (AI Mode in Search, Gemini app) and developer APIs. Omni Flash pricing was not disclosed in the article; developers will need to check Google AI Studio for current rates.