Nano Banana 2.1: pricing, context and benchmarks

What you need to know about Nano Banana 2.1

Google, based in United States, put Nano Banana 2.1 online on October 6, 2026. It accepts images and text as input and produces images and text. Its context window reaches 65,536 tokens, larger than 12 % of the models in the registry, and it can write up to 58,982 tokens in one go.

It is a recent model: real-world feedback and independent scores are still scarce.

Nano Banana 2.1 pricing

On OpenRouter, Nano Banana 2.1 costs $1.5 per million input tokens and $7.5 per million output tokens. Counting three tokens read for every token written, its average price is $3 per million, more expensive than 77 % of paid models (3.9 times the median of $0.76).

A concrete example: a task that sends 2,000 tokens (about 1,500 words) and receives a 500-token answer costs $0.0068. At 1,000 tasks a day, budget $203 a month. The price calculator redoes this with your own volumes.

Performance and benchmarks

Epoch AI does not yet publish a capabilities index for Nano Banana 2.1. We therefore show no made-up performance rating: only price, context and features count towards its score.

Features, privacy and local use

• It supports tool calling, so it can drive an AI agent, call APIs or MCP servers.
• It can answer in an enforced JSON format (structured outputs).
• It is a reasoning model: it "thinks" before answering, which helps on hard tasks but uses more output tokens.

Its weights are not published: it can only be used through the Google API or a broker such as OpenRouter, which means sending your data off your machines.

Other Google models