Nano Banana (Gemini 2.5 Flash Image)
Google's Nano Banana, also known as Gemini 2.5 Flash Image, is a model designed for both image generation and text processing. It supports multimodal inputs and outputs, allowing users to work with both images and text in a single workflow.
Nano Banana (Gemini 2.5 Flash Image) specs and pricing
- Provider: Google
- Released: October 7, 2025
- Context window: 33K tokens
- Max output: 8K tokens
- Input: images, text
- Output: images, text
- Price: $0.30 input / $2.50 output per 1M tokens
What Nano Banana (Gemini 2.5 Flash Image) is good at
- Generating images from text descriptions
- Analyzing visual content
- Creating multimodal content workflows
To-dos to try with Nano Banana (Gemini 2.5 Flash Image)
- Generate an image based on a detailed text prompt
- Describe the contents of an uploaded image
- Create a visual representation of a written concept
FAQ
- What is the primary function of Nano Banana? Nano Banana is an image generation model that also features contextual understanding of text.
- Can this model process images as input? Yes, the model accepts both image and text inputs.
- How much does Nano Banana (Gemini 2.5 Flash Image) cost? Nano Banana (Gemini 2.5 Flash Image) costs $0.30 per million input tokens and $2.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.19 credits ($1 = 100 credits).
- What is the context window of Nano Banana (Gemini 2.5 Flash Image)? Nano Banana (Gemini 2.5 Flash Image) can read up to 33K tokens at once and write up to 8K tokens in one reply.
- Can I use Nano Banana (Gemini 2.5 Flash Image) without coding? Yes. In todo.is you pick Nano Banana (Gemini 2.5 Flash Image) 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.