Nano Banana Pro Edit is Google’s image editing model exposed under the model id `google/nano-banana-pro/edit`. Google describes Nano Banana Pro as the “Nano Banana Pro (Gemini 3 Pro Image)” image generation and editing model, built on Gemini 3 Pro.
Google says Nano Banana Pro uses Gemini’s reasoning and real-world knowledge to improve how it visualizes information, and that it is designed for higher precision, depth, nuance, and detailed image editing.
| Developer | |
|---|---|
| Model ID | google/nano-banana-pro-edit |
| Release Date | February 26, 2026 |
| Modalities | Image, Text → Image |
Image generation and editing
Google identifies Nano Banana Pro as an image generation and editing model, not just a pure editor.
Built on Gemini 3 Pro
The model is described as being built on Gemini 3 Pro / Gemini 3 Pro Image.
Higher precision control
Google says it is designed for more precision, depth, nuance, and studio-quality control in image creation and edits.
Reasoning-aware visualization
Google states that the model uses Gemini’s state-of-the-art reasoning and real-world knowledge to visualize information better than before.
Google product branding
Google’s own documentation and product pages refer to the model as Nano Banana Pro and Gemini 3 Pro Image.
Image editing from an existing image
The model is presented as an image generation and editing system, and third-party API descriptions show an input pattern of existing image plus text prompt for edits.
High-precision visual generation
Google positions the model for detailed, nuanced visual creation where better understanding of the prompt matters.
Studio-style image workflows
Google’s product language emphasizes studio-quality precision and control for professional visual tasks.
Gemini 3 Pro Image
Google’s own naming shows this as the parent product name for Nano Banana Pro.
Gemini Image – Nano Banana
Google also uses a related Nano Banana branding for another Gemini image product, but that is a different model page and not the same exact model id.
Sources: https://blog.google/innovation-and-ai/products/nano-banana-pro/ · https://blog.google/products-and-platforms/products/gemini/where-to-use-nano-banana-pro/ · https://deepmind.google/models/gemini-image/pro/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Marketing and branding: the model is documented for updating campaign visuals without reshooting, which fits ad and brand asset refresh work.
Product photography: it is documented as useful for adjusting materials, lighting, or layout instantly, making it suited to fast product-image iteration.
Social media and content creation: it is documented as useful for generating multiple variations with minimal effort, which supports high-volume content production.
Artistic design: it is documented as useful for experimenting with colors, styles, and compositions effortlessly, making it suitable for creative image exploration.
import requests
r = requests.post(
"https://api.aimlapi.com/v1/images/generations",
headers={"Authorization": "Bearer " + AIMLAPI_KEY},
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",
"aspect_ratio": "16:9",
"resolution": "1K"
},
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"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",
"aspect_ratio": "16:9",
"resolution": "1K"
}),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/images/generations \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H "Content-Type: application/json" \
-d '{"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","aspect_ratio":"16:9","resolution":"1K"}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
Price shown is per generated image. Output resolution (1K, 2K, or 4K) is set via the `resolution` parameter, and up to 5 reference images can be passed via `image_urls`.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Nano Banana Pro Edit This page | Image generation | |||
| Image generation at scale | ||||
| Image generation at scale |
Nano Banana Pro Edit takes image, text as input and returns image.
Nano Banana Pro Edit became available on February 27, 2026.
Yes, Nano Banana Pro Edit accepts image input as well as a text prompt.
Nano Banana Pro Edit was built by Google.
Send a request to https://api.aimlapi.com/v1/images/generations with google/nano-banana-pro-edit as the model id.
Yes. Nano Banana Pro Edit is served through AI/ML API, so the same key and endpoint format used for other models applies.
The model ID is google/nano-banana-pro-edit.
It is classified as an image generation model.
