Gemini 3 Pro Image (Nano Banana Pro) overview
Gemini 3 Pro Image (Nano Banana Pro) by Google
Gemini 3 Pro Image, also known as Nano Banana Pro, is Google DeepMind’s latest state-of-the-art text-to-image generation model.
Gemini 3 Pro Image (Nano Banana Pro) specs
- Model ID
google/gemini-3-pro-image- Developer
- Context window
- 65,536 tokens
- Max output
- 32,768 tokens
- Input
- Text
- Output
- Image
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Gemini 3 Pro Image API Overview
Nano Banana Pro is designed for professional creators needing fast, high-quality visual content with deep reasoning and real-world knowledge integration. It supports generation of images up to 4K resolution with advanced control over effects like lighting, focus, and color grading.
Technical Specifications
- Base Architecture: Gemini 3 Pro / GEMPIX 2 architecture, a high-capacity multimodal image + text model
- Parameters: Scalable, around 8 billion in enterprise configurations.
- Resolution Support: Native 1K, 2K, and up to 4K output
Performance Benchmarks
Pro demonstrates substantial improvements in resolution clarity, artifact reduction, and physical accuracy versus predecessor Nano Banana (Gemini 2.5 Flash Image). It outperforms competitors in human-rated benchmarks focusing on prompt alignment, overall preference, and visual quality.
Image Generation at Professional Level
Gemini 3 Pro Image API focuses on creating original images from textual descriptions and contextual instructions. It is optimized for realism, composition accuracy, and reliable text rendering within images. The model understands complex prompts and translates them into visually consistent outputs that align with brand, style, and functional requirements.
From Concept to Visual in a Single Prompt
It transforms detailed text descriptions into complete, polished visuals. It supports a wide range of styles, from photorealistic scenes to clean, design-oriented graphics, making it suitable for marketing, UI concepts, and editorial illustrations.
Context-Aware Visual Reasoning
The model understands how objects, environments, and text interact in the real world. This enables the creation of images that feel logical and coherent, whether the output is a product mockup, an infographic, or a conceptual illustration.
Use cases
- Product photography and e-commerce image generation
- Marketing content (ads, banners, social media visuals)
- Brand storyboards and campaign visuals requiring consistent character/art style
- Apparel visualization and creative prototyping
- Multimodal scene generation and object blending
- Professional photography retouching and enhancement
Capabilities
- Function calling
- Reasoning
- Streaming
- Structured outputs
- Web search
Gemini 3 Pro Image (Nano Banana Pro) API pricing
| Usage | Price | Unit |
|---|---|---|
| Usage | $0.15 | per generation |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Gemini 3 Pro Image (Nano Banana Pro) vs other model models: prices
AI/ML API rates for 3 models, per generation.
| Model | Per generation |
|---|---|
 Gemini 3 Pro Image (Nano Banana Pro) | $0.15 |
| Gemini 2.5 Flash Image (Nano Banana) | $0.039 |
| Gemini 3 Pro Image | $0.25 |
How to use the Gemini 3 Pro Image (Nano Banana Pro) API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "google/gemini-3-pro-image",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "google/gemini-3-pro-image",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "google/gemini-3-pro-image",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Gemini 3 Pro Image (Nano Banana Pro)
Related articles
Gemini 3 Pro Image (Nano Banana Pro) FAQ
What is the context window of Gemini 3 Pro Image (Nano Banana Pro)?
Gemini 3 Pro Image (Nano Banana Pro) has a 65,536 tokens context window and can return up to 32,768 tokens.
What inputs and outputs does Gemini 3 Pro Image (Nano Banana Pro) support?
Gemini 3 Pro Image (Nano Banana Pro) takes image, text as input and returns text.
What is the model ID for Gemini 3 Pro Image (Nano Banana Pro)?
Use google/gemini-3-pro-image as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
How much does Gemini 3 Pro Image (Nano Banana Pro) cost?
Gemini 3 Pro Image (Nano Banana Pro) costs $0.15 per generation on AI/ML API, billed as you go with no subscription.
Does Gemini 3 Pro Image (Nano Banana Pro) support streaming?
Yes, Gemini 3 Pro Image (Nano Banana Pro) can stream responses as they are generated.
Can Gemini 3 Pro Image (Nano Banana Pro) read images?
Yes, Gemini 3 Pro Image (Nano Banana Pro) accepts image input alongside text.
Who created Gemini 3 Pro Image (Nano Banana Pro)?
Gemini 3 Pro Image (Nano Banana Pro) was built by Google.