Designers needing 4K and fine control of lighting and camera get the family's best, at about four times Nano Banana 2's price.

Kenning's take

What it does

Nano Banana Pro, or Gemini 3 Pro Image, is Google's image generation and editing model for complex, high-quality work. It is built on Gemini 3 Pro, renders clear text in several languages, and lets users change camera angles, lighting, focus and colour grading, with output up to 4K. It launched in the Gemini app, Google Ads, Workspace, NotebookLM and the Gemini API, and is now kept in the Gemini app for Google AI Pro and Ultra subscribers alongside the faster Nano Banana 2.

• Built on Gemini 3 Pro reasoning
• Legible text in multiple languages
• Camera angle, lighting, focus and colour controls
• 2K and 4K output with a range of aspect ratios
• SynthID watermark checks in the Gemini app

Who it suits. Designers, marketers and Gemini subscribers who need detailed, accurate images and infographics.

Key facts

Category

AI models

Part of

Google Gemini

Made by

Google DeepMind

Released

20 November 2025

How to get it

in the Gemini app (limited for free users, more for Google AI Plus, Pro and Ultra), NotebookLM, Google Ads, Slides and Vids, Flow for Ultra, and the Gemini API (gemini-3-pro-image) and Vertex AI

Works on

Web, iOS, Android, API

In the UK

Yes

Free plan

limited free quota in the Gemini app

API price

$2 per million input tokens, $120 per million image output tokens (about $0.134 per 1K/2K image, $0.24 per 4K); about half in Batch

FAQ

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