Google has released Nano Banana 2.1, an updated model for image generation and editing built on Gemini 3.6 Flash. Positioned as an efficient counterpart to the flagship Pro line, the model replaces Nano Banana 2—originally released in February 2026—and halves generation costs while introducing enhanced multi-image reference capabilities.
Lower Pricing and Flash-Tier Speed
Google has reduced generation prices for Nano Banana 2.1 compared to the previous version. Creating a 1K image now costs 3.36 cents, down from 6.70 cents, while 4K image pricing drops from 15.10 cents to 7.56 cents. For context, Nano Banana Pro charges 13.40 cents per 1K generation. Operating at Flash-tier speeds, Nano Banana 2.1 occasionally rivals Pro in synthetic benchmarks, though Google notes that Nano Banana Pro generally maintains superior visual quality in practice.
Multi-Reference Consistency and Search Tools
According to Google, Nano Banana 2.1 improves text rendering, infographics, wide panoramas, and overall image quality over earlier releases. The model allows users to provide up to 14 reference images simultaneously, maintaining consistency for up to four distinct characters and ten objects across sequential prompts. It also connects directly to Google Search and provides minimal, medium, and high thinking levels that adjust output detail based on processing time.
Platform Rollout and Model Deprecation
The model supports output resolutions in 1K, 2K, and 4K. Google is rolling out Nano Banana 2.1 across its ecosystem, including the Gemini app, AI Mode in Google Search, Google AI Studio, Flow by Google, Stitch by Google, Google Ads, and the Gemini Enterprise Platform. As part of this transition, Google plans to shut down its legacy gemini-3.1-flash-image model on October 29, 2026.
AI-generated editorial illustration; not a documentary photograph.
Source: Google's new image model Nano Banana 2.1 generates better images for less money
SIGNAL TITANS
Leave a Reply