Get started with the Gemini API

The Gemini API and Google AI Studio help you start working with Google's latest models and turn your ideas into applications that scale.

Python

import google.generativeai as genai

genai.configure(api_key="YOUR_API_KEY")
model = genai.GenerativeModel("gemini-1.5-flash")
response = model.generate_content("Explain how AI works")
print(response.text)

Node.js

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

const genAI = new GoogleGenerativeAI("YOUR_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });

const prompt = "Explain how AI works";

const result = await model.generateContent(prompt);
console.log(result.response.text());

REST

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=YOUR_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
  "contents": [{
    "parts":[{"text": "Write a story about a magic backpack."}]
    }]
   }'

Meet the models

Try Gemini in Google AI Studio

1.5 Flash

Our most balanced multimodal model with great performance for most tasks

1.5 Flash-8B

Our fastest and most cost-efficient multimodal model with great performance for high-frequency tasks

1.5 Pro

Our best performing multimodal model with features for a wide variety of reasoning tasks

Explore the API

Explore long context

Input millions of tokens to Gemini models and derive understanding from unstructured images, videos, and documents.

Solve tasks with fine-tuning

Modify the behavior of Gemini models to adapt to specific tasks, recognize data, and solve problems. Tune models with your own data to make production deployments more robust and reliable.

Generate structured outputs

Constrain Gemini to respond with JSON, a structured data format suitable for automated processing.

Start building with the Gemini API

Get started