Nano Banana 2.1 via the Tokenator API

What the model is for

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, mask- and ink-based editing, and factual accuracy, and renders photorealistic skin tones, detailed materials, lighting, and coherent backgrounds. It accepts text and image inputs, returns images with optional text, and supports 1K and 2K.

Specification

Full nameNano Banana 2.1
API IDnano-banana-2.1
Model vendorGemini
TypeImage generation
Context window—
Max output—
Image inputyes
Tokenator usage multiplier2×
BadgeNEW
Input modalitiestext, image
Supported API formats/v1/images/generations
Upstream providers1
Current statusavailable
Data updated2026-10-08

Upstream providers

ProviderMultiplier
AiPartners Ltd2×

A request goes to the first available provider by priority; if it fails, Tokenator switches to the next one.

Example request

curl
curl https://api.tokenator.top/v1/images/generations \
  -H "Authorization: Bearer sk-your-tokenator-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nano-banana-2.1",
    "prompt": "an isometric illustration of a server rack",
    "n": 1
  }'

FAQ about Nano Banana 2.1

What is the API ID of Nano Banana 2.1?

nano-banana-2.1 — put this into the model field of your request.

What does a generation request look like?

POST to /v1/images/generations with model, prompt and optionally n and size. The format matches the OpenAI Images API — only the base URL and the key change.

How do I set the image size?

With the size field, for example 1024x1024. The available set depends on the model; 2048x2048 is not supported everywhere, and even there the result sometimes comes back smaller — check the actual image.

What does one image cost?

Generations are taken from the key's image quota: one picture — 2×, and with n images per request it is n × the multiplier. See the documentation for details.

Can I edit an existing image?

No — this model only generates images from a prompt.

What comes back in the response?

A data array where each item holds a link to the finished image in the url field. Download the picture and store it on your side — the link is not meant for permanent hosting.