Nano Banana 2.1 API

image

Image generation by google

Fast Gemini image generation and editing up to 4K, with up to 14 reference images.

Call Nano Banana 2.1 from Node.js, Python, or any HTTP client. No GPU provisioning, no cold starts, no Docker images — just an API key and a prompt.

Pay per request. Powering 1M+ generations daily.

Nano Banana 2.1 sample output

Start in 60 seconds

Install the official SDK for Node.js or Python, drop in your API key, and generate your first image.

npm install getimg-ai
import GetimgAI from "getimg-ai";

const client = new GetimgAI();

const result = await client.images.generate({
    model: "gemini-nano-banana-2-1",
    prompt: "product photography of a single perfectly ripe yellow banana standing upright on a mirror-polished chrome pedestal",
    aspect_ratio: "1:1",
    resolution: "1K",
    output_format: "jpeg"
  });
console.log(result.data[0].url);

How Nano Banana 2.1 API works

Send a prompt, get an image URL back — one synchronous call.

1

Get your API key

Create a key in the Developer Dashboard. Add credit and start calling — you are billed per request.

2

Send a request

POST to /v2/images/generations with your prompt and output format.

3

Get your image

The response includes the image URL plus a usage object with the exact cost.

What you can build with Nano Banana 2.1

Every example uses the same authentication and works with the official getimg-ai and getimg SDKs, or plain HTTP.

Text to image

Generate an image using just a text prompt.

import GetimgAI from "getimg-ai";

const client = new GetimgAI();

const result = await client.images.generate({
    model: "gemini-nano-banana-2-1",
    prompt: "product photography of a single perfectly ripe yellow banana standing upright on a mirror-polished chrome pedestal",
    aspect_ratio: "1:1",
    resolution: "1K",
    output_format: "jpeg"
  });
console.log(result.data[0].url);

Image editing

Edit or restyle an existing image with an instruction-based prompt.

import GetimgAI from "getimg-ai";

const client = new GetimgAI();

const result = await client.images.generate({
    model: "gemini-nano-banana-2-1",
    prompt: "Restyle the subject in warm cinematic studio lighting.",
    aspect_ratio: "1:1",
    resolution: "1K",
    output_format: "jpeg",
    images: [
      {
        url: "https://your-bucket.s3.amazonaws.com/source.png"
      }
    ]
  });
console.log(result.data[0].url);

Multi-reference generation

Combine up to 14 reference images for character consistency, style, or composition guidance.

import GetimgAI from "getimg-ai";

const client = new GetimgAI();

const result = await client.images.generate({
    model: "gemini-nano-banana-2-1",
    prompt: "A product hero shot blending the style of the reference images.",
    aspect_ratio: "1:1",
    resolution: "1K",
    output_format: "jpeg",
    images: [
      {
        url: "https://your-bucket.s3.amazonaws.com/reference-1.png"
      },
      {
        url: "https://your-bucket.s3.amazonaws.com/reference-2.png"
      }
    ]
  });
console.log(result.data[0].url);

Nano Banana 2.1 pricing

Pay per image. No subscriptions, no minimums, no idle GPU costs.

Nano Banana 2.1

$0.04 – $0.135 /image

/v2/images/generations

Fast Gemini image generation and editing up to 4K, with up to 14 reference images.

ResolutionPriceImages for $10
1K$0.04 /image250
2K$0.065 /image153
4K$0.135 /image74

More from google

Other google models available through the same API.

Nano Banana 2.1 API — frequently asked questions

How do I use the Nano Banana 2.1 API?

Install the official Node.js (npm install getimg-ai) or Python (pip install getimg) SDK, or call the endpoint directly over HTTP from any client.

Make a POST request to /v2/images/generations with your API key and a JSON body containing the model ID (gemini-nano-banana-2-1) and a prompt. The response includes the generated image URL.

See the API documentation for the full parameter reference.

Which SDK should I use?

Use getimg-ai for Node.js and TypeScript projects, and getimg for Python. Both wrap the same REST API with typed inputs, retries, and built-in polling for video generations.

For other languages — Go, Rust, Java, Ruby, PHP — call the HTTP endpoints directly. Every example on this page includes a cURL snippet you can port to any HTTP client.

What resolutions does Nano Banana 2.1 support?

Nano Banana 2.1 supports the following resolutions: 1K, 2K, 4K across 13 aspect ratios (1:1, 2:3, 3:2, 4:3, 3:4, 4:5, 16:9, 9:16, 21:9, 1:4, 4:1, 1:8, 8:1).

How much does Nano Banana 2.1 cost?

Nano Banana 2.1 uses pay-per-image pricing with no subscriptions or minimum commitments. Rates vary by resolution. See the pricing table above for exact rates per image.

Does Nano Banana 2.1 support reference images?

Yes. Nano Banana 2.1 accepts up to 14 reference images. Reference images guide the generation toward a specific style, composition, or subject. See the example above.

Start building with Nano Banana 2.1

Grab an API key, install the SDK, ship image generation today.

Looking for other models? View all available models