Nano Banana 2.1
Summary
Nano Banana 2.1 is a language model from Google DeepMind, released on 6 Oct 2026. It accepts images and text and generates images and text, with a 66K-token context window and up to 59K output tokens per response.
Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...
Last verified 7 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | Google DeepMind |
|---|---|
| Release date | 6 Oct 2026 [OpenRouter] |
| Status | Generally available |
| Context window | 66K (65,536 tokens) [OpenRouter] |
| Max output | 59K tokens [OpenRouter] |
| Input | Images and text [OpenRouter] |
| Output | Images and text [OpenRouter] |
| Reasoning mode | Yes [OpenRouter] |
| Tool calling | Yes [OpenRouter] |
| Structured output | Yes [OpenRouter] |
Nano Banana 2.1 API pricing by provider
USD per million tokens. Sorted by input price.
We do not currently track a paid API listing for this model.
Frequently asked questions
What is the context window of Nano Banana 2.1?
Nano Banana 2.1 has a context window of 65,536 tokens (66K) and can generate up to 58,982 tokens in a single response, according to OpenRouter.
When was Nano Banana 2.1 released?
Google DeepMind released Nano Banana 2.1 on 6 Oct 2026, according to OpenRouter.
Change history
- No longer listed on openrouter
- Added to the directory
- Now listed on openrouter