Now Google's default image model, good for quick edits with accurate text; casual users get it free in Gemini.

Kenning's take

What it does

Nano Banana 2, also called Gemini 3.1 Flash Image, is a Google image model for generating and editing pictures quickly, with world knowledge, consistent characters, accurate text and grounding in Google image search. At launch it replaced Nano Banana Pro as the default image model in the Gemini app and became the default in Flow, AI Mode in Search and Google Ads. Developers can use it through Google AI Studio, the Gemini API and Vertex AI, where Google now lists Nano Banana 2.1 as its recommended successor.

• Image generation and conversational editing at Flash speed
• Character consistency across turns
• Accurate text rendering
• Grounding with Google web and image search
• 1K, 2K and 4K output
• SynthID watermark and C2PA Content Credentials

Who it suits. Gemini users making or editing images, and developers who need fast, cheap image generation.

Key facts

Category

AI models

Part of

Google Gemini

Made by

Google DeepMind

Released

26 February 2026

How to get it

in the Gemini app, AI Mode and Lens in Google Search, Flow and Google Ads, and through Google AI Studio, the Gemini API (gemini-3.1-flash-image) and Vertex AI

Works on

Web, iOS, Android, API

In the UK

Yes

Free plan

available in the Gemini app; no free tier in the Gemini API

API price

$1.50 per million input tokens, $30 per million image output tokens (about $0.0336 per 1K image, $0.0504 per 2K, $0.113 per 4K); half price in Batch

FAQ

Facts from the maker's own pages and the sources listed. Checked 2026-10-11.