Nano Banana 2.1
Google's Nano Banana 2.1 is an image generation and editing model designed for the Flash tier. It supports both text and image inputs and outputs, featuring built-in reasoning and tool-calling capabilities.
Nano Banana 2.1 specs and pricing
- Provider: Google
- Released: October 6, 2026
- Context window: 66K tokens
- Max output: 59K tokens
- Input: images, text
- Output: images, text
- Price: $1.50 input / $7.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Nano Banana 2.1 is good at
- Generating new images from text descriptions
- Editing existing images through recontextualization
- Tasks requiring integrated reasoning and tool usage
To-dos to try with Nano Banana 2.1
- Generate a high-quality image of a product in a new environment based on a provided photo
- Edit an existing image to change specific visual elements using text instructions
- Use tool-calling to process a complex request involving both text analysis and image generation
FAQ
- What is the primary function of Nano Banana 2.1? It is a model developed by Google specifically for image generation and editing tasks.
- Can this model process inputs other than text? Yes, it accepts both image and text inputs and can produce both image and text outputs.
- How much does Nano Banana 2.1 cost? Nano Banana 2.1 costs $1.50 per million input tokens and $7.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 5.25 credits ($1 = 100 credits).
- What is the context window of Nano Banana 2.1? Nano Banana 2.1 can read up to 66K tokens at once and write up to 59K tokens in one reply.
- Can I use Nano Banana 2.1 without coding? Yes. In todo.is you pick Nano Banana 2.1 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.