CLI Quickstart
Get up and running with Gemini from your terminal in under 5 minutes.
1
Get Your API Key
First, you'll need a Gemini API key from Google AI Studio.
Get API Key from AI Studio ↗2
Install the SDK
Install the Google Generative AI package for your preferred language.
Python
pip install google-generativeaiNode.js
npm install @google/generative-ai3
Configure Your API Key
Set your API key as an environment variable for security.
macOS / Linux
export GOOGLE_API_KEY="your-api-key-here"💡 Pro tip: Add this to your
~/.zshrc or ~/.bashrc to persist across sessions.4
Make Your First Request
Here's a complete example using Gemini 3 Flash.
Python
import google.generativeai as genai
import os
# Configure with API key
genai.configure(api_key=os.environ["GOOGLE_API_KEY"])
# Initialize the model
model = genai.GenerativeModel("gemini-3-flash")
# Generate content
response = model.generate_content("Explain quantum computing in 3 sentences")
print(response.text)Node.js
import { GoogleGenerativeAI } from "@google/generative-ai";
const genAI = new GoogleGenerativeAI(process.env.GOOGLE_API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-3-flash" });
async function run() {
const result = await model.generateContent(
"Explain quantum computing in 3 sentences"
);
console.log(result.response.text());
}
run();Common Patterns
📝 Text Generation
response = model.generate_content("Your prompt here")🖼️ Image Analysis
import PIL.Image
image = PIL.Image.open("image.jpg")
response = model.generate_content(["Describe this image", image])💬 Chat Conversation
chat = model.start_chat(history=[])
response = chat.send_message("Hello!")
response = chat.send_message("What did I just say?")⚡ Streaming Response
response = model.generate_content("Long prompt...", stream=True)
for chunk in response:
print(chunk.text, end="")Troubleshooting
"API key not found" error+
Make sure your environment variable is set correctly. Try running echo $GOOGLE_API_KEY to verify it's set.
"Model not found" error+
Check the model name spelling. Valid names include gemini-3-flash and gemini-3-pro.
Rate limit exceeded+
The free tier has request limits. Implement exponential backoff or upgrade to a paid plan for higher limits.