Nano Banana Standard: the stable 1K legacy route
- Stable model ID:
gemini-2.5-flash-image - LaoZhang API price: currently $0.025/call; confirm price and charges in the console
- Best for: Existing 1K workflows, simple generation, and low-cost compatibility
- For new projects: Compare the newer, faster Nano Banana 2 Lite
Prerequisites
1
Get API Key
Log in to laozhang.ai console to obtain your API key
2
Configure Billing Mode
Edit token settings and choose one of the following billing modes (same price for both):
- Volume Priority (Recommended): Uses balance billing first, automatically switches when balance is insufficient. Suitable for most users
- Pay-per-call: Direct deduction for each call. Suitable for strict budget control scenarios
Both modes have exactly the same price at $0.025/image, only the billing method differs.

Model Overview
Nano Banana Standard is the legacy market name for Google’s stablegemini-2.5-flash-image model. It provides 1K text-to-image through the chat completions interface and remains useful for existing integrations. Google recommends Nano Banana 2 Lite for new low-cost, high-frequency projects.
🚀 Lightning-Fast Generation
Generates high-quality images in just 10 seconds on average, faster than OpenAI series! Returns base64 format data for direct use.
API Console
Create an API key, review balance, and inspect call logs
Live Demo
YingTu AI - Try instantly, no code required
🌟 Core Features
- ⚡ Ultra-Fast Response: Generates in ~10 seconds on average, significantly faster than OpenAI series
- 💰 Cost-Controlled: $0.025/image, current price shown in console
- 🔄 Perfect Compatibility: Completely consistent with
gpt-4o-imageandsora_imagecalling methods - 📦 Base64 Output: Returns base64 encoded image data directly, no secondary download needed
- 🎨 Google Technology: Based on Google’s latest image generation technology, outstanding quality
📋 Model Comparison
⚠️ Important Notes
Return Format Differences
gemini-2.5-flash-image: Returns base64 encodingsora_image: Returns image URL- Calling method is exactly the same, only return format differs
🚀 Quick Start
Prerequisites
- Create Token: Login to LaoZhang API and create a pay-per-use type token

1
Login Console
Visit https://api2.laozhang.ai/token and login to your account
2
Create New Token
Click “Create New Token” button, make sure to select “Pay-per-use” type
3
Save Token
Copy and securely save the generated token, format is
sk-xxxxxx- Select Domain: Recommended to use
https://api2.laozhang.ai(globally accelerated). Overseas servers can directly connect tohttps://api-vip.laozhang.ai, but switch back to the primary domain if unstable
Basic Example - Curl
Complete Example - Python
Bash Script - Auto Save
🎯 Use Cases
1. Rapid Prototyping
2. Content Creation
💡 Best Practices
1. Prompt Optimization
2. Base64 Processing
📊 Performance Comparison
⚠️ Important Notes
- Token Type: Must use pay-per-use type token
- API Endpoint: Use
/v1/chat/completions, not/v1/images/generations - Return Format: Returns base64 encoding, requires manual decoding and saving
- Model Name:
gemini-2.5-flash-image(case-sensitive) - Request Format: Use chat format, put prompt in user message content
🔍 FAQ
What are the advantages of base64 format compared to URL?
What are the advantages of base64 format compared to URL?
Base64 returns image data directly, no secondary download needed, avoids URL expiration issues. Especially suitable for scenarios requiring immediate image processing.
How to switch from sora_image to Nano Banana?
How to switch from sora_image to Nano Banana?
Simply change the model name from
sora_image to gemini-2.5-flash-image, and modify result processing logic (from URL to base64).Are there limits for batch generation?
Are there limits for batch generation?
No concurrency limits, but it’s recommended to control concurrency for optimal performance.
🔗 Related Resources
Image Editing API
Edit existing images, multi-image composition
Nano Banana Pro
4K HD, complex instruction understanding
API Key Management
Create and manage tokens
Pricing
View detailed pricing
🎨 Pro Tip: Nano Banana model is particularly good at understanding complex scene descriptions and artistic styles. Utilizing detailed prompts can yield better results!