Nano Banana Pro Edit (Gemini 3 Pro Image Edit)

This documentation is valid for the following list of our models:

• google/nano-banana-pro-edit

• google/gemini-3-pro-image-preview-edit

Both IDs listed above refer to the same model; we support them for backward compatibility.

Try in Playground

Model Overview

Google’s smartest image-to-image model as of the November 2025 preview release. The model takes multiple images as input, with the prompt defining how they are used or combined.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post

Body

application/json

modelstring · enumRequiredPossible values:

promptstringRequired

The text prompt describing the content, style, or composition of the image to be generated.

image_urlsstring · uri[]Required

List of URLs or local Base64 encoded images to edit. Supports up to 14 images.

aspect_ratiostring · enumOptional

The aspect ratio of the generated image.

Default: 1:1Possible values:

resolutionstring · enumOptional

The size of the generated image.

Default: 1KPossible values:

num_imagesnumber · min: 1 · max: 4Optional

The number of images to generate.

Default: 1

providerstringOptional

Provider routing override. google runs native Google with no fallback; fal runs the fal.ai mirror; auto (default) uses the Google -> fal.ai fallback chain. Case-insensitive.

Example: auto

Responses

200Success

application/json

post/v1/images/generations

cURLJavaScriptPython

curl -L \
  --request POST \
  --url 'https://api.aimlapi.com/v1/images/generations' \
  --header 'Authorization: Bearer <YOUR_AIMLAPI_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
      "model": "google/nano-banana-pro-edit",
      "prompt": "Combine the images so the T-Rex is wearing a business suit, sitting in a cozy small café, drinking from the mug. Blur the background slightly to create a bokeh effect.",
      "image_urls": [
        "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/t-rex.png",
        "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/blue-mug.jpg"
      ]
    }'

200Success

{
  "data": [
    {
      "url": "https://cdn.aimlapi.com/generations/hedgehog/1749730923700-29fe35d2-4aef-4bc5-a911-6c39884d16a8.png",
      "b64_json": null
    }
  ],
  "meta": {
    "usage": {
      "credits_used": 120000
    }
  }
}

Quick Example

Generate an image with the specified quality and aspect ratio using two input images and a prompt that defines how the images should be edited.

Python

import requests
import json

def main():
    response = requests.post(
        "https://api.aimlapi.com/v1/images/generations",
        headers={
            # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
            "Authorization": "Bearer <YOUR_AIMLAPI_KEY>",
            "Content-Type": "application/json",
        },
        json={
            "model": "google/nano-banana-pro-edit",
            "image_urls": [
                "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/t-rex.png",
                "https://raw.githubusercontent.com/aimlapi/api-docs/main/reference-files/blue-mug.jpg"
            ],
            "prompt": "Combine the images so the T-Rex is wearing a business suit, sitting in a cozy small café, drinking from the mug. Blur the background slightly to create a bokeh effect.",
            "aspect_ratio": "16:9",
            "resolution": "1K"
        }
    )

    data = response.json()
    print(json.dumps(data, indent=2, ensure_ascii=False))

if __name__ == "__main__":
    main()

JS

Response

{
  "description": "",
  "data": [
    {
      "url": "https://cdn.aimlapi.com/flamingo/files/b/koala/qnutcal6jcrPr43jMp_Xg.png",
      "content_type": "image/png",
      "width": null,
      "height": null,
      "file_name": "qnutcal6jcrPr43jMp_Xg.png"
    }
  ],
  "meta": {
    "usage": {
      "tokens_used": 315000
    }
  }
}

Reference Images	Generated Image

Here’s an example of the output using alternative resolution and aspect_ratio parameters:

"aspect_ratio": "16:9", "resolution": "2K"