nano-banana-pro
Nano Banana Pro is Google's state-of-the-art image generation and editing model — the strongest reasoning tier in the Nano Banana line. Multi-image fusion up to 14 references, output up to 4K, configurable safety filtering, and an optional fallback model for batch throughput.
Input
Describe the image to generate, or the edit to apply when input images are provided.
Optional reference images (up to 14). Empty = text-to-image; populated = editing, multi-image fusion, or character-consistency runs.
0 / 14
Output resolution. 4K runs at roughly 2× the per-image cost of 1K / 2K — use it for print-grade deliverables.
Output aspect ratio. `match_input_image` inherits from the first reference image.
Output file format.
Content safety strictness. `block_only_high` is the most permissive (default); `block_low_and_above` is the strictest. Use stricter modes for kid-facing surfaces and ad networks with tight content rules.
When true, the request falls back to a cheaper model (currently Seedream 5) if the Pro model is at capacity. Useful for batch pipelines that prioritise throughput over absolute fidelity.
Output
Run the model to see output here.
Examples
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/google/nano-banana-pro \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'