Gemini API reference

The Gemini API lets you access the latest generative models from Google. This API reference provides detailed information for the classes and methods available in the Gemini API SDKs. Pick a language and follow the setup steps to get started with building generative applications on your platform of choice.

Python Node.js Go Dart (Flutter) Android Swift Web

Prerequisites

This quickstart assumes that you're familiar with building applications with Python.

To complete this quickstart, ensure that your development environment meets the following requirements:

• Python 3.9+

Install the Gemini API SDK

The Python SDK for the Gemini API is contained in the google-generativeai package. Install the dependency using pip:

pip install -q -U google-generativeai

Set up your API key

To use the Gemini API, you'll need an API key. If you don't already have one, create a key in Google AI Studio.

Get an API key from Google AI Studio

Then, configure your key.

It is strongly recommended that you do not check an API key into your version control system but assign it as an environment variable instead:

export API_KEY=<YOUR_API_KEY>

Import the library

Import and configure the Google Generative AI library.

import google.generativeai as genai
import os

genai.configure(api_key=os.environ["API_KEY"])

Make your first request

Use the generateContent method to generate text.

model = genai.GenerativeModel("gemini-1.5-flash")
response = model.generate_content("Write a story about a magic backpack.")
print(response.text)
text_generation.py

What's next

Now that you have a model client, you can start programming with the Gemini API. You can find the Python SDK docs on GitHub, or read through the reference to learn how to use key API features:

• Generating content
• Working with models
• Understanding tokens

If you're just getting started, check out the following guides, which will help you understand the Gemini API programming model:

• Gemini API quickstart
• Gemini model guide
• About generative models
• Introduction to prompt design

You might also want to check out the capabilities guides, which introduce Gemini API features and provide examples of programming with the SDKs:

• Text generation
• Tokens
• Prompting with media files
• Context caching
• Embeddings
• Tuning

Then, for more in-depth documentation of Gemini API methods and request parameters, browse the guides in this reference.