Nano Banana Pro Text-to-Image

🚀 Nano Banana Pro (Gemini 3) Now Available! This is Google’s most powerful image generation model.

4K Quality: Supports 1K, 2K, 4K resolutions
Ultra Intelligent: Based on Gemini 3 architecture, precise understanding of complex prompts
Best Value: Only **0.09/image∗∗(62.50.09/image** (62.5% cheaper than official 0.09/image∗∗(62.50.24)

🎁 Free Trial

🚀 Live Demo

AI Images - Try instantly, no code required

Prerequisites

1 Get API Key Login to YeLIn AI console to get your API key 2 Configure Billing Mode Edit token settings and select one of these billing modes (same price):

Pay-per-use Priority (Recommended): Use balance first, auto-switch when insufficient. Best for most users
Pay-per-use: Direct charge per request. Best for strict budget control

Both modes have identical pricing at $0.09/image, only the billing method differs.

请在 Console 查看对应界面截图。

API calls will fail without proper billing configuration. Complete this setup first!

Model Overview

Nano Banana Pro is LaoZhang API’s custom name for Google’s Gemini 3 Pro Image Preview (gemini-3-pro-image-preview) model. Designed for professional use cases requiring ultimate image quality and complex semantic understanding.

Core Advantages

🌟 Native 4K Resolution: Generate up to 4096×4096 ultra-high-definition images.
🧠 Gemini 3 Intelligence: Built-in logical reasoning, understands abstract descriptions like “a cat looking at an empty bowl with disappointment after missing breakfast”.
💪 Complex Composition: Precise control over object placement, quantity, and text rendering.
💰 Best Price: $0.09/image for premium image generation use cases.

🌟 Core Features

⚡ Fast Response: ~10 seconds average, significantly faster than OpenAI series
💰 Great Value: 0.09/image(62.50.09/image (62.5% cheaper than official 0.09/image(62.50.24)
🔄 Dual Compatibility: Supports OpenAI SDK and Google native formats
📐 Flexible Sizes: Google native format supports 10 aspect ratios
🖼️ High Resolution: Supports 1K, 2K, 4K resolutions
🧠 Thinking Mode: Built-in reasoning process, optimizes composition before generation (enabled by default)
🌐 Search Grounding: Supports Google Search for fact verification and image generation
🎨 Multi-Image Reference: Supports up to 14 reference images (6 objects + 5 characters, etc.)
📦 Base64 Output: Returns base64 encoded image data directly, no secondary download needed

🔀 Two API Modes

Nano Banana Pro supports two endpoints, each with unique advantages:

Feature	OpenAI Compatible Mode	Google Native Format
Endpoint	`/v1/chat/completions`	`/v1beta/models/gemini-3-pro-image-preview:generateContent`
Model Name	`gemini-3-pro-image-preview`	Specified in URL
Image Size	Fixed 1:1	10 aspect ratios
Resolution	Fixed 1K	1K/2K/4K
Compatibility	Perfect with OpenAI SDK	Requires native calls
Return Format	Base64	Base64
Use Case	Quick migration, simple needs	Custom sizes or high resolution

💡 How to Choose?

For square (1:1) images only, use OpenAI Compatible Mode - simpler
For widescreen (16:9), portrait (9:16), or other specific ratios or high-res (2K/4K), use Google Native Format

📋 Model Comparison

Comparison with Other Image Models

Model	Model ID	Billing	LaoZhang API Price	Official Price	Savings	Resolution	Speed
Nano Banana Pro	`gemini-3-pro-image-preview`	Per-use	$0.09/image	$0.24/image	62.5%	1K/2K/4K	~10s
Nano Banana2	`gemini-3.1-flash-image-preview`	Per-use	$0.055/image	-	-	1K/2K/4K	~10s
Nano Banana	`gemini-2.5-flash-image`	Per-use	$0.025/image	$0.04/image	37.5%	1K (fixed)	~10s
GPT-Image-1	`gpt-image-1`	Token-based	10input/10 input/10input/40 output per M	-	-	-	Medium
Flux Kontext Pro	`flux-kontext-pro`	Per-use	$0.035/image	$0.04/image	12.5%	-	Fast
Sora Image	`sora_image`	Per-use	$0.01/image	-	-	-	Slower

💰 Price Advantage Details

Nano Banana Pro: 0.09/image(LaoZhangAPI)vs0.09/image (LaoZhang API) vs 0.09/image(LaoZhangAPI)vs0.24/image (official), 62.5% cheaper
Bonus: Get +10% bonus on large deposits
Exchange Rate: Paying in CNY is even more cost-effective

Nano Banana Pro offers exceptional value at LaoZhang API!

🚀 Quick Start

Prerequisites

1 Create Token Login to LaoZhang API Token Management and create a pay-per-use type token（截图请在 Console 查看） 2 Select Billing Type Important: Must select “Pay-per-use” type, not “Pay-as-you-go” 3 Save Token Copy the generated token in format sk-xxxxxx

Method 1: OpenAI Compatible Mode (1:1 Images)

Best for quick integration, generates 1024x1024 (1K) images by default.

Basic Example - Curl

curl -X POST "https://api.yelinai.com/v1/chat/completions" \
     -H "Authorization: Bearer $API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
    "model": "gemini-3-pro-image-preview",
    "stream": false,
    "messages": [
        {
            "role": "user",
            "content": "a beautiful sunset over mountains"
        }
    ]
}'

Python SDK Example

from openai import OpenAI
import base64
import re

client = OpenAI(
    api_key="sk-YOUR_API_KEY",
    base_url="https://api.yelinai.com/v1"
)

response = client.chat.completions.create(
    model="gemini-3-pro-image-preview",
    messages=[
        {
            "role": "user",
            "content": "a beautiful sunset over mountains"
        }
    ]
)

# Extract base64 image data
content = response.choices[0].message.content
match = re.search(r'!\[.*?\]\((data:image/png;base64,.*?)\)', content)

if match:
    base64_data = match.group(1).split(',')[1]
    image_data = base64.b64decode(base64_data)

    with open('output.png', 'wb') as f:
        f.write(image_data)
    print("✅ Image saved: output.png")

Method 2: Google Native Format (Custom Aspect Ratio + 4K)

Best for 4K resolution or custom aspect ratio needs.

Supported Aspect Ratios

Type	Aspect Ratio Options
Landscape	21:9 (Ultra-wide), 16:9 (Widescreen), 4:3, 3:2
Square	1:1
Portrait	9:16 (Vertical), 3:4, 2:3
Other	5:4, 4:5

Supported Resolutions

Aspect Ratio	1K Resolution	2K Resolution	4K Resolution
1:1	1024×1024	2048×2048	4096×4096
16:9	1376×768	2752×1536	5504×3072
9:16	768×1376	1536×2752	3072×5504
4:3	1200×896	2400×1792	4800×3584
3:4	896×1200	1792×2400	3584×4800
21:9	1584×672	3168×1344	6336×2688
3:2	1248×832	2496×1664	4992×3328
2:3	832×1248	1664×2496	3328×4992
5:4	1152×896	2304×1792	4608×3584
4:5	896×1152	1792×2304	3584×4608

💡 Resolution Selection Guide

1K: Best for web display, social media, quick previews
2K: Best for high-quality printing, professional display
4K: Best for large prints, professional design, extreme detail

Complete Curl Example (Text-to-Image 4K)

#!/bin/bash

# 1. Set API Key
export API_KEY="sk-YOUR_API_KEY"

# 2. Send request (Generate 4K image with Nano Banana Pro)
curl -s -X POST "https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "A futuristic city skyline at sunset, high detailed, 4k"}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["IMAGE"],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "4K"
      }
    }
  }' \
  | jq -r '.candidates[0].content.parts[0].inlineData.data' \
  | base64 --decode > output_4k.png

echo "✅ Image saved: output_4k.png"

Python Code Examples

💡 Progressive Examples Example 1 generates image → Example 2 transforms its style → Example 3 fuses both images. Clear progression! Example 1: Text-to-Image → Generate First Image

import requests
import base64

# ========== Configuration ==========
API_KEY = "sk-YOUR_API_KEY"
API_URL = "https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent"
PROMPT = "A cute orange cat"
ASPECT_RATIO = "1:1"
IMAGE_SIZE = "2K"  # Nano Banana Pro supports: 1K, 2K, 4K
# ============================

headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}

payload = {
    "contents": [{"parts": [{"text": PROMPT}]}],
    "generationConfig": {
        "responseModalities": ["IMAGE"],
        "imageConfig": {
            "aspectRatio": ASPECT_RATIO,
            "imageSize": IMAGE_SIZE
        }
    }
}

response = requests.post(API_URL, headers=headers, json=payload, timeout=180)
result = response.json()

# Save image
image_data = result["candidates"][0]["content"]["parts"][0]["inlineData"]["data"]
with open("output.png", "wb") as f:
    f.write(base64.b64decode(image_data))

print("✅ Image saved: output.png")

Example 2: Image-to-Image → Use First Image to Generate Second

import requests
import base64

# ========== Configuration ==========
API_KEY = "sk-YOUR_API_KEY"
API_URL = "https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent"

INPUT_IMAGE = "output.png"  # Use image from Example 1
PROMPT = "Transform this image into Van Gogh Starry Night style oil painting"
ASPECT_RATIO = "1:1"
IMAGE_SIZE = "2K"
# ============================

# Read and encode image
with open(INPUT_IMAGE, "rb") as f:
    image_b64 = base64.b64encode(f.read()).decode("utf-8")

headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}

payload = {
    "contents": [{
        "parts": [
            {"text": PROMPT},
            {"inline_data": {"mime_type": "image/jpeg", "data": image_b64}}
        ]
    }],
    "generationConfig": {
        "responseModalities": ["IMAGE"],
        "imageConfig": {
            "aspectRatio": ASPECT_RATIO,
            "imageSize": IMAGE_SIZE
        }
    }
}

response = requests.post(API_URL, headers=headers, json=payload, timeout=180)
result = response.json()

# Save image
output_data = result["candidates"][0]["content"]["parts"][0]["inlineData"]["data"]
with open("output_styled.png", "wb") as f:
    f.write(base64.b64decode(output_data))

print("✅ Image saved: output_styled.png")

Example 3: Multi-Image Mix → Use First and Second to Generate Third

import requests
import base64

# ========== Configuration ==========
API_KEY = "sk-YOUR_API_KEY"
API_URL = "https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent"

# Use the two images from Example 1 and Example 2
IMAGES = ["output.png", "output_styled.png"]
PROMPT = "Fuse these two images into an artwork"
ASPECT_RATIO = "16:9"
IMAGE_SIZE = "2K"
# ============================

# Build parts: text + multiple images
parts = [{"text": PROMPT}]

for img_path in IMAGES:
    with open(img_path, "rb") as f:
        img_b64 = base64.b64encode(f.read()).decode("utf-8")
    parts.append({"inline_data": {"mime_type": "image/png", "data": img_b64}})

headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}

payload = {
    "contents": [{"parts": parts}],
    "generationConfig": {
        "responseModalities": ["IMAGE"],
        "imageConfig": {
            "aspectRatio": ASPECT_RATIO,
            "imageSize": IMAGE_SIZE
        }
    }
}

response = requests.post(API_URL, headers=headers, json=payload, timeout=180)
result = response.json()

# Save image
output_data = result["candidates"][0]["content"]["parts"][0]["inlineData"]["data"]
with open("output_mixed.png", "wb") as f:
    f.write(base64.b64decode(output_data))

print("✅ Image saved: output_mixed.png")

Complete Demo Script (All Three Scenarios)

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Nano Banana Pro Image Generation - Complete Demo Script
Includes three scenarios: text-to-image, single image-to-image, multi-image mix
"""

import requests
import base64
import os
from datetime import datetime

# ========== Configuration ==========
API_KEY = "sk-YOUR_API_KEY"
API_URL = "https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent"
# ============================

def generate_text_to_image(prompt, aspect_ratio="16:9", image_size="2K"):
    """Scenario 1: Text-to-Image"""
    print(f"\n📸 Text-to-Image: {prompt}")

    payload = {
        "contents": [{"parts": [{"text": prompt}]}],
        "generationConfig": {
            "responseModalities": ["IMAGE"],
            "imageConfig": {
                "aspectRatio": aspect_ratio,
                "imageSize": image_size
            }
        }
    }

    return call_api(payload, f"text_{image_size}")

def generate_image_to_image(input_image, prompt, aspect_ratio="1:1", image_size="2K"):
    """Scenario 2: Single Image-to-Image"""
    print(f"\n🎨 Image-to-Image: {input_image}")

    with open(input_image, "rb") as f:
        img_b64 = base64.b64encode(f.read()).decode("utf-8")

    payload = {
        "contents": [{
            "parts": [
                {"text": prompt},
                {"inline_data": {"mime_type": "image/jpeg", "data": img_b64}}
            ]
        }],
        "generationConfig": {
            "responseModalities": ["IMAGE"],
            "imageConfig": {
                "aspectRatio": aspect_ratio,
                "imageSize": image_size
            }
        }
    }

    return call_api(payload, f"styled_{image_size}")

def generate_multi_image_mix(images, prompt, aspect_ratio="16:9", image_size="2K"):
    """Scenario 3: Multi-Image Mix"""
    print(f"\n🖼️  Multi-Image Mix: {len(images)} images")

    parts = [{"text": prompt}]
    for img in images:
        with open(img, "rb") as f:
            parts.append({"inline_data": {"mime_type": "image/jpeg", "data": base64.b64encode(f.read()).decode()}})

    payload = {
        "contents": [{"parts": parts}],
        "generationConfig": {
            "responseModalities": ["IMAGE"],
            "imageConfig": {
                "aspectRatio": aspect_ratio,
                "imageSize": image_size
            }
        }
    }

    return call_api(payload, f"mixed_{image_size}")

def call_api(payload, prefix):
    """Call API"""
    headers = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}

    try:
        response = requests.post(API_URL, headers=headers, json=payload, timeout=180)
        result = response.json()

        image_data = result["candidates"][0]["content"]["parts"][0]["inlineData"]["data"]
        filename = f"{prefix}_{datetime.now().strftime('%Y%m%d_%H%M%S')}.png"

        with open(filename, "wb") as f:
            f.write(base64.b64decode(image_data))

        print(f"✅ Saved: {filename}")
        return filename
    except Exception as e:
        print(f"❌ Error: {e}")
        return None

# ========== Main Program ==========
def main():
    print("🎨 Nano Banana Pro Image Generation - Complete Demo")

    # Scenario 1: Text-to-Image
    img1 = generate_text_to_image(
        "A futuristic cyberpunk city at night, 4k",
        aspect_ratio="16:9",
        image_size="4K"
    )

    # Scenario 2: Image-to-Image (requires test_cat.jpg)
    if os.path.exists("test_cat.jpg"):
        img2 = generate_image_to_image(
            "test_cat.jpg",
            "Van Gogh Starry Night style",
            aspect_ratio="1:1",
            image_size="2K"
        )

    # Scenario 3: Multi-Image Mix (requires test_cat.jpg, test_apple.jpg)
    if os.path.exists("test_cat.jpg") and os.path.exists("test_apple.jpg"):
        generate_multi_image_mix(
            ["test_cat.jpg", "test_apple.jpg"],
            "A cat eating an apple",
            aspect_ratio="16:9",
            image_size="2K"
        )

    print("\n✅ Demo complete!")

if __name__ == "__main__":
    main()

Bash Script Example

Expand to view complete Bash script (with aspect ratio config)

#!/bin/bash

# ============================================================
# Nano Banana Pro Image Generation Tool - Bash/Curl Version
# Supports 4K resolution and multiple aspect ratios
# ============================================================

# ========== Configuration ==========
API_KEY="sk-YOUR_API_KEY"
API_URL="https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent"
PROMPT="A futuristic cyberpunk city at night, neon lights, flying cars, highly detailed, 4k"
ASPECT_RATIO="16:9"
IMAGE_SIZE="4K"  # 1K, 2K, 4K

OUTPUT_FILE="gemini_\`$\{IMAGE_SIZE}_$(date +%Y%m%d_%H%M%S).png"
# ============================

# Check dependencies
if ! command -v jq &> /dev/null; then
    echo "❌ Error: jq tool required"
    echo ""
    echo "Installation:"
    echo "  macOS:   brew install jq"
    echo "  Ubuntu:  sudo apt-get install jq"
    echo "  CentOS:  sudo yum install jq"
    exit 1
fi

echo "============================================================"
echo "Nano Banana Pro Image Generation Tool"
echo "============================================================"
echo "⏰ Start time: $(date '+%Y-%m-%d %H:%M:%S')"
echo "🚀 Generating image..."
echo "📝 Prompt: \`$\{PROMPT}"
echo "📐 Aspect Ratio: \`$\{ASPECT_RATIO}"
echo "🖼️  Resolution: \`$\{IMAGE_SIZE}"

# Build JSON request
REQUEST_JSON=$(jq -n \
  --arg prompt "$PROMPT" \
  --arg ratio "$ASPECT_RATIO" \
  --arg size "$IMAGE_SIZE" \
  '{
    contents: [{
      parts: [{text: $prompt}]
    }],
    generationConfig: {
      responseModalities: ["IMAGE"],
      imageConfig: {
        aspectRatio: $ratio,
        imageSize: $size
      }
    }
  }')

# Send request
RESPONSE=$(curl -s -X POST "\`$\{API_URL}" \
  -H "Authorization: Bearer \`$\{API_KEY}" \
  -H "Content-Type: application/json" \
  -d "\`$\{REQUEST_JSON}")

# Check for errors
if echo "\`$\{RESPONSE}" | jq -e '.error' &> /dev/null; then
    echo "❌ Generation failed"
    echo "💥 Error message:"
    echo "\`$\{RESPONSE}" | jq -r '.error.message // .error'
    exit 1
fi

# Extract image data
echo "💾 Saving image..."
IMAGE_DATA=$(echo "\`$\{RESPONSE}" | jq -r '.candidates[0].content.parts[0].inlineData.data' 2>/dev/null)

if [ -z "$IMAGE_DATA" ] || [ "$IMAGE_DATA" = "null" ]; then
    echo "❌ No image data found"
    exit 1
fi

# Decode and save image
echo "\`$\{IMAGE_DATA}" | base64 --decode > "\`$\{OUTPUT_FILE}"

# Check result
if [ -f "\`$\{OUTPUT_FILE}" ]; then
    FILE_SIZE=$(du -h "\`$\{OUTPUT_FILE}" | cut -f1)
    echo "✅ Image saved: \`$\{OUTPUT_FILE}"
    echo "📊 File size: \`$\{FILE_SIZE}"
    echo "============================================================"
    echo "🎉 Generation successful!"
    echo "⏰ End time: $(date '+%Y-%m-%d %H:%M:%S')"
else
    echo "❌ Image save failed"
    exit 1
fi

🚀 Gemini 3 Pro Advanced Features (Nano Banana Pro Exclusive)

🧠 Thinking Mode

Nano Banana Pro has built-in reasoning capability that automatically optimizes composition and logic before generating images to ensure higher quality output. This feature is enabled by default, no extra configuration needed. 💡 Thinking Mode Advantages

Automatically optimizes composition and layout
Understands complex multi-step instructions
Creates temporary “thinking images” during generation (backend only, no extra charge)
Final output is higher quality and more aligned with expectations

🌐 Google Search Grounding

The model can use Google Search as a tool to generate images using real-time data (weather, stock prices, news).

curl -s -X POST "https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart."}]}],
    "tools": [{"google_search": {}}],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {"aspectRatio": "16:9"}
    }
  }'

Note: When using search grounding, responseModalities must include "TEXT" (i.e., ["TEXT", "IMAGE"]). Pure image mode cannot return search results.

🎨 Multi-Image Reference (Reference Images)

Nano Banana Pro supports mixing up to 14 reference images:

Up to 6 high-fidelity object images (for inclusion in final image)
Up to 5 person images (for maintaining character consistency)

# Multi-Image Reference Example (Python)
import requests
import base64

API_KEY = "sk-YOUR_API_KEY"
API_URL = "https://api.yelinai.com/v1beta/models/gemini-3-pro-image-preview:generateContent"

# Prepare multiple reference images
image_paths = ["cat.jpg", "apple.jpg"]
parts = [{"text": "Combine these images: a cat eating an apple on a table"}]

for path in image_paths:
    with open(path, "rb") as f:
        image_data = base64.b64encode(f.read()).decode("utf-8")
    parts.append({
        "inline_data": {
            "mime_type": "image/jpeg",
            "data": image_data
        }
    })

# Send request
response = requests.post(
    API_URL,
    headers={
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    },
    json={
        "contents": [{"parts": parts}],
        "generationConfig": {
            "responseModalities": ["IMAGE"],
            "imageConfig": {
                "aspectRatio": "16:9",
                "imageSize": "2K"
            }
        }
    }
)

💡 Multi-Image Reference Best Practices

Object images: For product composition, scene building
Person images: Maintain character appearance consistency (for image series)
Combined use: Create complex visual narratives

💡 Best Practices

Prompt Optimization

Clear Description

Use specific, detailed descriptions including subject, style, color, lighting, etc.

Reference Style

Specify art styles: “oil painting style”, “watercolor”, “cyberpunk style”, etc.

Avoid Vagueness

Avoid overly abstract or vague terms

English First

English prompts typically work better, but Chinese is also supported

Aspect Ratio Selection Guide

Use Case	Recommended Ratio
Social media landscape	16:9
Phone wallpaper/vertical	9:16
Instagram square	1:1
Print photos	4:3 or 3:2
Movie posters	2:3
Banner ads	21:9

❓ FAQ

How to test Nano Banana Pro API for free?

Visit api.yelinai.com to register
Automatically receive $0.5 free credit
Create token and select “Pay-per-use”
Call the gemini-3-pro-image-preview model

$0.5 can be applied toward multiple Nano Banana Pro requests. What is the Nano Banana Pro API price?

Channel	Price	Notes
LaoZhang API	$0.09/image	62.5% cheaper than official
Google Official	$0.24/image	Full price

Register to get $0.5 credit toward usage. How to test Nano Banana Pro API online? Method 1: API Playground visual testingMethod 2: Curl command

curl -X POST "https://api.yelinai.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{"model": "gemini-3-pro-image-preview", "messages": [{"role": "user", "content": "a cute cat"}]}'

What’s the difference between Nano Banana Pro and Nano Banana?

Feature	Nano Banana Pro	Nano Banana
Model	`gemini-3-pro-image-preview`	`gemini-2.5-flash-image`
Technology	Gemini 3	Gemini 2.5
Resolution	1K/2K/4K	1K (fixed)
Price	$0.09/image	$0.025/image
Thinking Mode	✅ Yes	❌ No
Search Grounding	✅ Yes	❌ No
Multi-Image Reference	Up to 14	Up to 3

How to choose the API mode?

For 1:1 square images only, use OpenAI Compatible Mode - simpler
For specific aspect ratios (like 16:9 widescreen) or high-res (2K/4K), use Google Native Format

How to use 4K resolution? 4K is only supported by Nano Banana Pro, use Google native format and add imageSize parameter:

{
  "generationConfig": {
    "responseModalities": ["IMAGE"],
    "imageConfig": {
      "aspectRatio": "16:9",
      "imageSize": "4K"
    }
  }
}

Important: Must use uppercase “K” (1K, 2K, 4K). Does it support Chinese prompts? Perfectly supported! Gemini 3 Pro has top-tier multilingual understanding. You can describe scenes in Chinese directly, no translation needed. How to get better generation results?

Detailed description: Provide specific details (color, style, scene, etc.)
English prompts: English typically works better
Reference style: Specify art style (like “oil painting style”, “watercolor”)
Multiple attempts: Try different prompts, pricing is affordable

How to use the returned Base64 data? Base64 data can be displayed directly in web pages:

<img src="data:image/png;base64,iVBORw0KG..." />

Or decode and save as file (see code examples above)

Pro Image Editing

Learn how to edit and transform existing images with Nano Banana Pro

Nano Banana2 Image Generation

$0.055/image, better value Banana2 version

Standard Image Generation

More affordable Nano Banana Standard version

Token Management

Create and manage your API tokens

Pricing

View detailed pricing and billing information

📝 Changelog

2025-01: Nano Banana Pro standalone documentation launched 🚀 Nano Banana Pro Dedicated Page

Split from combined documentation into dedicated Pro version
Complete 4K resolution usage guide
Detailed advanced features (thinking mode, search grounding, multi-image reference)
Complete code examples and best practices
Comparison with Nano Banana Standard

​🎁 Free Trial

​🚀 Live Demo

​Prerequisites

​Model Overview

​Core Advantages

​🌟 Core Features

​🔀 Two API Modes

​📋 Model Comparison

​Comparison with Other Image Models

​🚀 Quick Start

​Prerequisites

​Method 1: OpenAI Compatible Mode (1:1 Images)

​Basic Example - Curl

​Python SDK Example

​Method 2: Google Native Format (Custom Aspect Ratio + 4K)

​Supported Aspect Ratios

​Supported Resolutions

​Complete Curl Example (Text-to-Image 4K)

​Python Code Examples

​Bash Script Example

​🚀 Gemini 3 Pro Advanced Features (Nano Banana Pro Exclusive)

​🧠 Thinking Mode

​🌐 Google Search Grounding

​🎨 Multi-Image Reference (Reference Images)

​💡 Best Practices

​Prompt Optimization

​Clear Description

​Reference Style

​Avoid Vagueness

​English First

​Aspect Ratio Selection Guide

​❓ FAQ

​🔗 Related Resources

​Pro Image Editing

​Nano Banana2 Image Generation

​Standard Image Generation

​Token Management

​Pricing

​📝 Changelog

🎁 Free Trial

🚀 Live Demo

Prerequisites

Model Overview

Core Advantages

🌟 Core Features

🔀 Two API Modes

📋 Model Comparison

Comparison with Other Image Models

🚀 Quick Start

Prerequisites

Method 1: OpenAI Compatible Mode (1:1 Images)

Basic Example - Curl

Python SDK Example

Method 2: Google Native Format (Custom Aspect Ratio + 4K)

Supported Aspect Ratios

Supported Resolutions

Complete Curl Example (Text-to-Image 4K)

Python Code Examples

Bash Script Example

🚀 Gemini 3 Pro Advanced Features (Nano Banana Pro Exclusive)

🧠 Thinking Mode

🌐 Google Search Grounding

🎨 Multi-Image Reference (Reference Images)

💡 Best Practices

Prompt Optimization

Clear Description

Reference Style

Avoid Vagueness

English First

Aspect Ratio Selection Guide

❓ FAQ

🔗 Related Resources

Pro Image Editing

Nano Banana2 Image Generation

Standard Image Generation

Token Management

Pricing

📝 Changelog