Google Unveils Nano Banana 2 Lite: Fast and Affordable Image Model

By Priya Anand

Google has introduced the Nano Banana 2 Lite, officially known as the Gemini 3.1 Flash Lite Image, marking its fastest and most cost-effective image-generation model to date. Announced on June 30, 2026, the model is designed to produce text-to-image outputs in approximately four seconds, significantly faster than the 20 seconds required by its predecessor, the standard Nano Banana 2.

Priced at $0.034 per 1,000 images, the Nano Banana 2 Lite enables high-volume image workflows at a reduced cost. This makes it an attractive option for users prioritizing speed and cost-efficiency over image quality.

The model is accessible through Google AI Studio, the Gemini API, and the Gemini Enterprise Agent Platform. It is also being integrated across various Google services, including AI Mode in Google Search, the Gemini app, and Google Photos.

While the Nano Banana 2 Lite excels in rapid prototyping, it may not be suitable for tasks requiring high precision, such as small text rendering and infographics. Despite these limitations, user evaluations via Arena.ai suggest that the model's performance is nearly on par with the non-Lite version.

This release is part of Google's broader strategy to replace the original Nano Banana model, now deemed a legacy product, with more efficient solutions. The launch coincides with the introduction of Gemini Omni Flash for video generation, facilitating seamless transitions from image creation to animation.