Intermediate

API & Integration

Generate API keys, integrate Gemini into your applications with Python, JavaScript, and curl, and understand rate limits and pricing.

Generating API Keys

Your API key is the gateway to using Gemini in your applications:

1. Open Google AI Studio
2. Click "Get API key" in the left sidebar
3. Click "Create API key in new project" (or select an existing project)
4. Copy the key and store it securely (you won't be able to see it again)

Gemini API Quickstart

The Gemini API uses a REST interface. Here are quickstart examples in three languages:

Python

pip install google-generativeai

import google.generativeai as genai
import os

# Configure with your API key
genai.configure(api_key=os.environ["GEMINI_API_KEY"])

# Create a model instance
model = genai.GenerativeModel("gemini-pro")

# Generate content
response = model.generate_content("Explain quantum computing in simple terms.")
print(response.text)

# Multi-turn chat
chat = model.start_chat()
response = chat.send_message("What is machine learning?")
print(response.text)
response = chat.send_message("How does it differ from deep learning?")
print(response.text)

JavaScript (Node.js)

npm install @google/generative-ai

const { GoogleGenerativeAI } = require("@google/generative-ai");

const genAI = new GoogleGenerativeAI(process.env.GEMINI_API_KEY);

async function run() {
  const model = genAI.getGenerativeModel({ model: "gemini-pro" });

  // Simple generation
  const result = await model.generateContent(
    "Write a haiku about programming."
  );
  console.log(result.response.text());

  // Multi-turn chat
  const chat = model.startChat();
  const chatResult = await chat.sendMessage("What is TypeScript?");
  console.log(chatResult.response.text());
}

run();

curl (REST API)

# Simple text generation
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent?key=$GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [{"text": "List 5 uses of AI in healthcare."}]
    }]
  }'

# With generation config
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-pro:generateContent?key=$GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Write a creative story opener."}]}],
    "generationConfig": {
      "temperature": 0.9,
      "topK": 40,
      "topP": 0.95,
      "maxOutputTokens": 1024
    }
  }'

SDK Setup

Official SDKs are available for multiple languages:

Language	Package	Install Command
Python	google-generativeai	pip install google-generativeai
JavaScript	@google/generative-ai	npm install @google/generative-ai
Kotlin/Android	generativeai	Add via Gradle dependency
Swift/iOS	GoogleGenerativeAI	Add via Swift Package Manager
Go	google.golang.org/genai	go get google.golang.org/genai

Rate Limits

The free tier provides generous limits for development and prototyping:

Model	Requests per Minute	Tokens per Minute	Requests per Day
Gemini Pro	60	32,000	1,500
Gemini Flash	60	1,000,000	1,500

For higher limits, upgrade to a paid plan or use the API through Google Cloud's Vertex AI.

Pricing

Google AI Studio offers a generous free tier:

• Free tier: Rate-limited but sufficient for development and small projects
• Pay-as-you-go: Charged per token (input and output priced separately)
• Gemini Flash: Significantly cheaper than Pro for high-volume use
• Tuned models: Priced similarly to the base model they're built on

Using with Google Cloud

For production workloads, consider using the Gemini API through Vertex AI on Google Cloud:

• Higher rate limits and SLAs for production use
• VPC-SC and data residency controls
• Integration with other Google Cloud services
• Enterprise support and compliance certifications
• Access to additional models and features