Gemini 2.5 Flash Image Generation

Model Overview

Gemini 2.5 Flash Image (gemini-2.5-flash-image) is Google’s official release image generation model, more stable and reliable than the preview version (gemini-2.5-flash-image-preview). Supports both OpenAI-compatible format and Google native format.

🎉 Official Release

✅ Stable and reliable, recommended for production
🎨 Supports custom aspect ratios (16:9, 9:16, and 10 other ratios)
⚡ Generates high-quality images in ~10 seconds
💰 Great value: $0.025/image (37.5% cheaper than official)

🔀 Two Calling Methods

Gemini Flash Image supports two API endpoints, each with advantages:

Feature	OpenAI Compatible Mode	Google Native Format
Endpoint	`/v1/chat/completions`	`/v1beta/models/gemini-2.5-flash-image:generateContent`
Model Name	`gemini-2.5-flash-image`	Specified in URL
Image Size	Fixed 1:1	Supports 10 aspect ratios
Compatibility	Perfect OpenAI SDK compatibility	Requires native calling
Return Format	Base64	Base64
Use Case	Quick migration, simple needs	Custom dimensions needed
Aspect Ratio	❌ No	✅ 21:9, 16:9, 4:3, 3:2, 1:1, 9:16, 3:4, 2:3, 5:4, 4:5

💡 How to Choose?

If you only need square (1:1) images, use OpenAI Compatible Mode for simplicity
If you need widescreen (16:9), portrait (9:16), or other specific ratios, use Google Native Format

🌟 Key Features

⚡ Fast Response: ~10 seconds generation, significantly faster than OpenAI series
💰 Great Value: $0.025/image, 37.5% cheaper than official ($ 0.04/image)
🔄 Dual Compatibility: Supports both OpenAI SDK and Google native format
📐 Flexible Sizes: Google native format supports 10 aspect ratios
📦 Base64 Output: Returns base64-encoded image data directly, no secondary download needed
🎨 Google Technology: Based on Google’s latest image generation technology, excellent quality

📋 Model Comparison

Model	Model ID	Billing	LaoZhang Price	Official Price	Savings	Speed
Gemini Flash Image	`gemini-2.5-flash-image`	Per Request	$0.025/image	$0.04/image	37.5%	~10s
GPT-Image-1	`gpt-image-1`	Per Token	$10 input/$ 40 output per M	-	-	Medium
Flux Kontext Pro	`flux-kontext-pro`	Per Request	$0.035/image	$0.04/image	12.5%	Fast
Sora Image	`sora_image`	Per Request	$0.01/image	-	-	Slower

💡 Pricing Advantage

37.5% cheaper than official price
Top up $100 get +10% bonus, combined with exchange rate advantage, total ~73% of official price
Transparent and predictable pricing, no need to worry about token consumption

🚀 Quick Start

Prerequisites

Create Token

Select Billing Method

Important: Must select “Per-Request Billing” type, not “Pay-As-You-Go”

Save Token

Copy the generated token, format is sk-xxxxxx

💰 Detailed Pricing Advantage

LaoZhang API Price: $0.025/image (37.5% cheaper than official)
Official Price: $0.04/image
Top-up Bonus: Top up $100 get +10% bonus
Exchange Rate Advantage: Combined advantage equals ~73% of official price

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

Basic Example - Curl

curl -X POST "https://api.laozhang.ai/v1/chat/completions" \
     -H "Authorization: Bearer $API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
    "model": "gemini-2.5-flash-image",
    "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.laozhang.ai/v1"
)

response = client.chat.completions.create(
    model="gemini-2.5-flash-image",
    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 Ratios)

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

Simple Curl Example

curl -s -X POST "https://api.laozhang.ai/v1beta/models/gemini-2.5-flash-image:generateContent" \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [
        {"text": "a beautiful sunset over mountains"}
      ]
    }],
    "generationConfig": {
      "responseModalities": ["IMAGE"],
      "imageConfig": {
        "aspectRatio": "16:9"
      }
    }
  }' \
  | jq -r '.candidates[0].content.parts[0].inlineData.data' \
  | base64 --decode > output.png

Complete Python Tool Script

Expand to view complete Python script (with aspect ratio support)

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""
Gemini Image Generation Tool - Python Version
Generate images using Google Gemini 2.5 Flash Image model with custom aspect ratios

Supported aspect ratios:
- Landscape: 21:9, 16:9, 4:3, 3:2
- Square: 1:1
- Portrait: 9:16, 3:4, 2:3
- Other: 5:4, 4:5
"""

import requests
import base64
import os
import datetime
from typing import Optional, Tuple

class GeminiImageGenerator:
    """Gemini Image Generator"""

    # Supported aspect ratios
    SUPPORTED_ASPECT_RATIOS = [
        "21:9", "16:9", "4:3", "3:2", "1:1",
        "9:16", "3:4", "2:3", "5:4", "4:5"
    ]

    def __init__(self, api_key: str, api_url: str = "https://api.laozhang.ai/v1beta/models/gemini-2.5-flash-image:generateContent"):
        """
        Initialize image generator

        Args:
            api_key: API key
            api_url: API URL (defaults to Google native Gemini API)
        """
        self.api_key = api_key
        self.api_url = api_url
        self.headers = {
            "Content-Type": "application/json",
            "Authorization": f"Bearer {api_key}"
        }

    def generate_image(self, prompt: str, aspect_ratio: Optional[str] = "1:1",
                      output_dir: str = ".") -> Tuple[bool, str]:
        """
        Generate image and save locally

        Args:
            prompt: Image description (prompt)
            aspect_ratio: Aspect ratio like "16:9", "1:1" etc (default 1:1)
            output_dir: Output directory (default current directory)

        Returns:
            (success, message)
        """
        print(f"🚀 Starting image generation...")
        print(f"📝 Prompt: {prompt}")
        print(f"📐 Aspect Ratio: {aspect_ratio}")

        # Validate aspect ratio
        if aspect_ratio and aspect_ratio not in self.SUPPORTED_ASPECT_RATIOS:
            return False, f"Unsupported aspect ratio {aspect_ratio}. Supported: {', '.join(self.SUPPORTED_ASPECT_RATIOS)}"

        # Generate filename
        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
        output_file = os.path.join(output_dir, f"gemini_{timestamp}.png")

        try:
            # Build request payload
            payload = {
                "contents": [{
                    "parts": [{"text": prompt}]
                }]
            }

            # Add aspect ratio config
            if aspect_ratio:
                payload["generationConfig"] = {
                    "responseModalities": ["IMAGE"],
                    "imageConfig": {
                        "aspectRatio": aspect_ratio
                    }
                }

            print("📡 Sending request to Gemini API...")

            # Send request
            response = requests.post(
                self.api_url,
                headers=self.headers,
                json=payload,
                timeout=120
            )

            if response.status_code != 200:
                return False, f"API request failed, status code: {response.status_code}"

            # Parse response
            result = response.json()

            # Extract image data
            if "candidates" not in result or len(result["candidates"]) == 0:
                return False, "Image data not found"

            candidate = result["candidates"][0]
            if "content" not in candidate or "parts" not in candidate["content"]:
                return False, "Response format error"

            parts = candidate["content"]["parts"]
            image_data = None

            for part in parts:
                if "inlineData" in part and "data" in part["inlineData"]:
                    image_data = part["inlineData"]["data"]
                    break

            if not image_data:
                return False, "Image data not found"

            # Decode and save image
            print("💾 Saving image...")
            decoded_data = base64.b64decode(image_data)

            os.makedirs(os.path.dirname(output_file) if os.path.dirname(output_file) else ".", exist_ok=True)

            with open(output_file, 'wb') as f:
                f.write(decoded_data)

            file_size = len(decoded_data) / 1024  # KB
            print(f"✅ Image saved: {output_file}")
            print(f"📊 File size: {file_size:.2f} KB")

            return True, f"Successfully saved image: {output_file}"

        except requests.exceptions.Timeout:
            return False, "Request timeout (120 seconds)"
        except requests.exceptions.ConnectionError:
            return False, "Network connection error"
        except Exception as e:
            return False, f"Error: {str(e)}"

def main():
    """Main function - usage example"""

    # ========== Configuration ==========
    # 1. Set your API key
    API_KEY = "sk-YOUR_API_KEY"

    # 2. Input image description (prompt)
    PROMPT = "a beautiful sunset over mountains"

    # 3. Select aspect ratio (optional)
    # Supported: 21:9, 16:9, 4:3, 3:2, 1:1, 9:16, 3:4, 2:3, 5:4, 4:5
    ASPECT_RATIO = "16:9"  # Widescreen
    # ASPECT_RATIO = "1:1"   # Square
    # ASPECT_RATIO = "9:16"  # Portrait

    # 4. Set output directory (optional)
    OUTPUT_DIR = "."  # Current directory
    # ============================

    print("="*60)
    print("Gemini Image Generation Tool")
    print("="*60)
    print(f"⏰ Start time: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    print("="*60)

    # Create generator and generate image
    generator = GeminiImageGenerator(API_KEY)
    success, message = generator.generate_image(
        prompt=PROMPT,
        aspect_ratio=ASPECT_RATIO,
        output_dir=OUTPUT_DIR
    )

    # Display result
    print("\n" + "="*60)
    if success:
        print("🎉 Generation successful!")
        print(f"✅ {message}")
    else:
        print("❌ Generation failed")
        print(f"💥 {message}")
        print("\nSuggestions:")
        print("  1. Check if API key is correct")
        print("  2. Check network connection")
        print("  3. Check if prompt is reasonable")

    print(f"⏰ End time: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    print("="*60)

if __name__ == "__main__":
    main()

Bash Script Example

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

#!/bin/bash

# ============================================================
# Gemini Image Generation Tool - Bash/Curl Version
# Generate images using Google Gemini 2.5 Flash Image model
# ============================================================

# ========== Configuration ==========
# 1. Set your API key
API_KEY="sk-YOUR_API_KEY"

# 2. Input image description (prompt)
PROMPT="a beautiful sunset over mountains"

# 3. Select aspect ratio (optional)
# Supported: 21:9, 16:9, 4:3, 3:2, 1:1, 9:16, 3:4, 2:3, 5:4, 4:5
ASPECT_RATIO="16:9"  # Widescreen
# ASPECT_RATIO="1:1"   # Square
# ASPECT_RATIO="9:16"  # Portrait

# 4. Set output filename
OUTPUT_FILE="gemini_generated_$(date +%Y%m%d_%H%M%S).png"

# 5. API endpoint
API_URL="https://api.laozhang.ai/v1beta/models/gemini-2.5-flash-image:generateContent"
# ============================

# 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"
    echo ""
    exit 1
fi

echo "============================================================"
echo "Gemini Image Generation Tool"
echo "============================================================"
echo "⏰ Start time: $(date '+%Y-%m-%d %H:%M:%S')"
echo "============================================================"
echo "🚀 Starting image generation..."
echo "📝 Prompt: ${PROMPT}"
echo "📐 Aspect Ratio: ${ASPECT_RATIO}"
echo "📡 Sending request to Gemini API..."

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

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

# Check errors
if echo "${RESPONSE}" | jq -e '.error' &> /dev/null; then
    echo "❌ Generation failed"
    echo "💥 Error message:"
    echo "${RESPONSE}" | jq -r '.error.message // .error'
    echo ""
    echo "Suggestions:"
    echo "  1. Check if API key is correct"
    echo "  2. Check network connection"
    echo "  3. Check if prompt is reasonable"
    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 "❌ Image data not found"
    echo "📋 Response content:"
    echo "${RESPONSE}" | jq '.' 2>/dev/null || echo "${RESPONSE}"
    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 "============================================================"
    echo "🎉 Generation successful!"
    echo "⏰ End time: $(date '+%Y-%m-%d %H:%M:%S')"
    echo "============================================================"
else
    echo "❌ Failed to save image"
    exit 1
fi

💡 Best Practices

Prompt Optimization

Clear Description

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

Reference Styles

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

Avoid Ambiguity

Avoid overly abstract or vague terms

English Preferred

English prompts usually work better, though Chinese is also supported

Aspect Ratio Selection Guide

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

❓ FAQ

How to choose calling method?

If you only need 1:1 square images, use OpenAI Compatible Mode for simplicity and perfect compatibility with existing code
If you need specific aspect ratios (like 16:9 widescreen), use Google Native Format
Both methods have the same price of $0.025/image

What aspect ratios are supported?

Google native format supports 10 aspect ratios:

Landscape: 21:9, 16:9, 4:3, 3:2
Square: 1:1
Portrait: 9:16, 3:4, 2:3
Other: 5:4, 4:5

What's the difference from Preview version?

Official Release (gemini-2.5-flash-image): Stable and reliable, recommended for production
Preview (gemini-2.5-flash-image-preview): Being deprecated, migration recommended
Price, speed, and quality are identical, just update the model name to migrate

How to get better generation results?

Detailed Description: Provide specific details (colors, style, scene, etc.)
English Prompts: English usually works better
Reference Styles: Specify art styles (e.g., “oil painting style”, “watercolor”)
Multiple Attempts: Try different prompts, prices are affordable

How to use returned Base64 data?

Base64 data can be displayed directly in web pages:

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

Or decode and save as a file (refer to code examples above)

Image Editing

Learn how to edit and transform existing images with Gemini Flash Image

API Reference

View complete API interface documentation

Token Management

Create and manage your API tokens

Pricing Details

View detailed pricing table and billing information

Getting Started

Core API

Video Generation APIs

Image Generation APIs

AI Understanding

Gemini 2.5 Flash Image Generation

Model Overview

🔀 Two Calling Methods

🌟 Key Features

📋 Model Comparison

🚀 Quick Start

Prerequisites

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

Basic Example - Curl

Python SDK Example

Method 2: Google Native Format (Custom Aspect Ratios)

Supported Aspect Ratios

Simple Curl Example

Complete Python Tool Script

Bash Script Example

💡 Best Practices

Prompt Optimization

Clear Description

Reference Styles

Avoid Ambiguity

English Preferred

Aspect Ratio Selection Guide

❓ FAQ

Image Editing

API Reference

Token Management

Pricing Details

Getting Started

Core API

Video Generation APIs

Image Generation APIs

AI Understanding

​Model Overview

​🔀 Two Calling Methods

​🌟 Key Features

​📋 Model Comparison

​🚀 Quick Start

​Prerequisites

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

​Basic Example - Curl

​Python SDK Example

​Method 2: Google Native Format (Custom Aspect Ratios)

​Supported Aspect Ratios

​Simple Curl Example

​Complete Python Tool Script

​Bash Script Example

​💡 Best Practices

​Prompt Optimization

Clear Description

Reference Styles

Avoid Ambiguity

English Preferred

​Aspect Ratio Selection Guide

​❓ FAQ

​🔗 Related Resources

Image Editing

API Reference

Token Management

Pricing Details

Model Overview

🔀 Two Calling Methods

🌟 Key Features

📋 Model Comparison

🚀 Quick Start

Prerequisites

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

Basic Example - Curl

Python SDK Example

Method 2: Google Native Format (Custom Aspect Ratios)

Supported Aspect Ratios

Simple Curl Example

Complete Python Tool Script

Bash Script Example

💡 Best Practices

Prompt Optimization

Aspect Ratio Selection Guide

❓ FAQ

🔗 Related Resources