Deprecated in the API with conflicting shutdown dates, so developers should move to a newer Nano Banana model rather than build on this.

Kenning's take

What it does

Gemini 2.5 Flash Image, nicknamed Nano Banana, generates and edits images from text and keeps people and pets looking consistent across edits. It can blend several photos, apply multi-turn edits and copy styles between images. It launched in the Gemini app and the API in August 2025; Google now lists it as deprecated, with newer Nano Banana models replacing it.

• Character consistency across edits
• Blending several photos into one scene
• Multi-turn conversational editing
• Style transfer between images
• SynthID invisible watermark

Who it suits. People editing photos in the Gemini app and developers building image tools.

Key facts

Category

AI models

Part of

Google Gemini

Made by

Google

Based in

United States

Released

26 August 2025

How to get it

Was launched in the Gemini app and the Gemini API, AI Studio and Vertex AI; deprecated in the API, with Google's pages giving conflicting shutdown dates (2 October 2026 on the pricing page, 15 March 2027 in the deprecations table)

Works on

API, Web

In the UK

Yes

Free plan

No free API tier listed

API price

$0.30 per million input tokens (text/image); image output $30 per million tokens, about $0.039 per image

FAQ

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