Google Updates Nano Banana AI with Better Features and Lower Costs

Google has unveiled Nano Banana 2.1, the latest iteration of its AI model that converts text into images or edits existing photos. The update is now available in the Gemini app, Google Search's AI Mode, Google Ads, and various developer tools like Google AI Studio, Flow, and Stitch.

The original Nano Banana model contributed significantly to the success of Gemini, helping it reach the top of app stores in September 2025 by transforming selfies into collectible figurines. This achievement also propelled Alphabet's market value to over $3 trillion.

Nano Banana 2.1 introduces three key improvements: enhanced visual design, more precise mask-based editing, and better subject consistency, ensuring objects and people retain their appearance across multiple edits. The model scored 1,050 ELO Points in text-to-image tests, outperforming Nano Banana 2 (990 points) and Nano Banana Pro (935 points).

The new version can handle up to 14 reference images simultaneously, tracking four characters and ten objects, and produces up to 4K resolution images. Developers can adjust the model's thinking time before generating images and ground results in Google Search and Google Image Search. The cost for a standard 1K image via the developer API is now $0.0336, half the price of Nano Banana 2's $0.067. A 4K image costs $0.0756, down from $0.151, making it a cost-effective option for bulk processing.