Imagen 3
Image Generationby Google
Google's state-of-the-art image generation model, available through the Gemini API and Vertex AI. Excels in photorealistic images with SynthID watermarking.
Registration & API Key Steps
Get Google AI API Key
Visit Google AI Studio and sign in with your Google account. Generate an API key for free.
Open linkChoose API Platform
Use the Gemini Developer API (free tier available) or Vertex AI (pay-as-you-go with GCP billing).
Install SDK
Install the Google Generative AI SDK for your preferred language (Python, Node.js, Go, etc.).
Start Generating Images
Use Imagen 3 model via the SDK. Images include an invisible SynthID watermark.
Pricing
| Tier | Price | Features |
|---|---|---|
| Gemini API Free Tier | Free (up to 1,500 images/day) | No credit card required, Up to 45,000 images/month, Full model access |
| Gemini API Paid (1K/2K) | $0.039 / image (1024x1024) | 1024x1024 or 2048x2048, Higher rate limits, Commercial use |
| Vertex AI | $0.134 / image (1K-2K) or $0.24 (4K) | Enterprise features, SLA guarantees, 4K resolution support |
Application Tips
Incredibly Generous Free Tier
Google AI Studio free tier offers 1,500 images/day (45,000/month) at no cost. This is the most generous free tier among all image generation APIs.
SynthID Watermark
All images include an invisible SynthID watermark identifying them as AI-generated. This cannot be removed.
Use Gemini 3 Pro for Image Editing
For image editing and manipulation, Gemini 3 Pro Image model supports text-guided image editing in addition to generation.
China Access Solutions
Vertex AI via GCP
Google Cloud Platform is accessible in China for enterprise customers. Apply for Vertex AI access through GCP.
API Proxy
Use a relay server in a supported region to proxy requests to the Gemini API.
Code Example
import { GoogleGenAI } from '@google/genai';
const ai = new GoogleGenAI({ apiKey: process.env.GOOGLE_API_KEY });
async function generateImage() {
const response = await ai.models.generateImages({
model: 'imagen-3.0-generate-002',
prompt: 'A photorealistic image of a golden retriever puppy in a garden',
config: {
numberOfImages: 1,
aspectRatio: '1:1',
},
});
// The response contains base64-encoded image data
const imageData = response.generatedImages[0].image.imageBytes;
const buffer = Buffer.from(imageData, 'base64');
require('fs').writeFileSync('output.png', buffer);
console.log('Image saved as output.png');
}
generateImage();Rate Limits
| Tier | Limits |
|---|---|
| Free Tier | 1,500 images/day, rate limited |
| Paid Tier | Higher limits, contact Google for details |
Recommended Use Cases
Related API Guides
DALL-E 3
OpenAI
OpenAI's most advanced image generation model, capable of creating highly detailed and accurate images from text descriptions with excellent prompt following.
Midjourney
Midjourney Inc.
Industry-leading AI image generation known for stunning artistic quality. No official public API yet; access via Discord bot or third-party API services.
Stable Diffusion API
Stability AI
Stability AI's official API for Stable Diffusion models including SD 3.5, Stable Image Core, and Stable Image Ultra. Open-source models also available for self-hosting.
Ideogram
Ideogram AI
AI image generation specializing in accurate text rendering within images. Excellent for logos, posters, and designs requiring readable text.