Text to image
Elo · text-to-image arena
Custom pricing for production workloads
Nano Banana Pro is a text-to-image model that generates images from text descriptions.
Nano Banana Pro is Google's Gemini 3 Pro Image model for high-precision image generation and editing.
google/nano-banana-proPOST https://api.aimlapi.com/v1/images/generationsNano Banana Pro is Google’s Gemini 3 Pro Image model, described by Google as a state-of-the-art image generation and editing model built on Gemini 3 Pro.
Google positions it for higher-precision image creation, with better understanding of prompts, improved detail, and stronger support for editing workflows.
| Developer | |
|---|---|
| Model ID | google/nano-banana-pro |
| Release Date | February 26, 2026 |
| Modalities | Image, Text → Image |
Model identity
Nano Banana Pro is the public nickname for Gemini 3 Pro Image.
Purpose
Google describes it as an image generation and editing model designed for complex, multi-turn image work.
Reasoning foundation
It is built on Gemini 3 Pro and uses Gemini’s reasoning and world knowledge to visualize information more effectively.
Inputs and outputs
Google AI Studio lists text and image inputs for Nano Banana Pro, and the model page shows image output options including 1K, 2K, and 4K.
Complex image editing
Google Cloud documentation says it is suited for challenging image generation and editing tasks that benefit from improved accuracy and image quality.
High-precision visual generation
Google says it is intended to create visuals with greater precision, depth, nuance, and detail.
Text-rich image creation
Google highlights improved legible text rendering as a capability of Nano Banana Pro.
Workspace and productivity content
Google Workspace says Nano Banana Pro is being rolled out in tools such as Slides, Vids, the Gemini app, and NotebookLM.
Nano Banana 2
Google Cloud identifies Nano Banana 2 as Gemini 3.1 Flash Image, while Nano Banana Pro is Gemini 3 Pro Image.
Original Nano Banana
Google’s image-generation overview distinguishes Nano Banana Pro from the earlier Nano Banana model used in Gemini image creation.
Sources: https://aistudio.google.com/models/nano-banana · https://blog.google/innovation-and-ai/products/nano-banana-pro/ · https://blog.google/innovation-and-ai/technology/ai/nano-banana-2/
Nano Banana Pro is documented as suited to creating prototypes, including turning ideas into visual mockups and designs. It is also suited to making infographics from data or source material, including concise visual explanations and slide-ready graphics. Another documented use is turning handwritten notes or sketches into diagrams and other structured visuals. Google also describes it as useful for creating polished slide decks and visual narratives from sources in NotebookLM and Slides.
Human-preference results for Nano Banana Pro in text to image, next to models available on AI/ML API. Data retrieved Nov 3, 2026.
Elo · text-to-image arena
USD per generation
Arena results for models you can call with the same API key.
Blind pairwise human votes on images generated from text prompts. Nano Banana Pro ranks #12 of 98.
| Usage | Price | Unit |
|---|---|---|
| Image generation | $0.25 | per generation |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
AI/ML API rates for 5 models, per generation.
| Model | Per generation |
|---|---|
| $0.25 | |
| $0.039 | |
| $0.04 | |
| $0.15 | |
| $0.15 |
Give your agent the model details, code and documentation.
export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"curl 'https://api.aimlapi.com/v1/images/generations' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "google/nano-banana-pro",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "google/nano-banana-pro",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}
response = requests.post("https://api.aimlapi.com/v1/images/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = 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",
"prompt": "A ginger cat asleep on a stack of exactly three hardcover books in a rainy bookshop window at dusk. Gold lettering on the glass reads OPEN LATE. Warm lamp light inside, raindrops and blurred neon reflections outside, 35mm film photo."
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Nano Banana Pro costs $0.25 per generation on AI/ML API, billed as you go with no subscription.
Nano Banana Pro takes image, text as input and returns image.
Nano Banana Pro became available on February 27, 2026.
Yes, Nano Banana Pro accepts image input as well as a text prompt.
Nano Banana Pro was built by Google.
Send a request to https://api.aimlapi.com/v1/images/generations with google/nano-banana-pro as the model id.
Yes. Nano Banana Pro is served through AI/ML API, so the same key and endpoint format used for other models applies.
Use google/nano-banana-pro as the model parameter. Requests go to https://api.aimlapi.com/v1/images/generations with your AI/ML API key.