Nano Banana 2.1
Nano Banana 2.1 is Google's October 2026 refresh of its fast Flash-tier image model: one model for text-to-image, conversational editing and fusion of up to 14 reference images. It reasons through the prompt before it renders, so lighting briefs, exact wording and structured layouts such as infographics land more reliably than on Nano Banana 2, for about half the credits at 1K and 2K.
Input
Describe the image to generate, or the edit to apply when input images are provided.
Optional reference images (up to 14). Leave empty for text-to-image; add one or more to edit, fuse references or keep characters and products consistent.
0 / 14
Output resolution. Use 2K for text-heavy graphics and 4K for print files. Higher tiers cost more per image.
Output aspect ratio. `match_input_image` follows the first reference image; also includes the banner shapes 1:4, 4:1, 1:8 and 8:1.
Output file format.
Use Google Image Search grounding so the model can pull web images as visual references. Also turns on web search.
Use Google Web Search grounding so the model can include real-time facts such as current products, events or places.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/google/nano-banana-2.1 \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'