Get started with the Gemini API

The Gemini API and Google AI Studio help you start working with Google's latest models. Access the whole Gemini model family and turn your ideas into real applications that scale.
Solve complex reasoning problems with a model designed to balance flexibility, speed, and cost efficiency.
Reduce big data down to human scale. Analyze and understand data with large token context windows.

Try Gemini 1.5 in AI Studio
Combine text, images, video, and audio to create rich data contexts and solve complex reasoning problems.

Explore the Gemini API's capabilities

Discover how to create custom AI models, connect them to existing systems, and reason over your content with state of the art embeddings in the Gemini API.
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.
Get up-to-date information from your business systems and take action based on users requests. Function calling lets you use the Gemini API to take plain language requests and map them to programming interfaces.
Find content, answer questions, generate specific content, classify data, and map random requests to specific actions. Text embeddings help you understand, navigate, and act on your content and business data.

Build apps with the Gemini API

Start building with Gemini API using tutorials, application templates, and example code.
Build a coding assistant tool for generating code, code comments, or performing other coding assistance.
Find problems, discover trends, and investigate results using your own business data. Use Gemini API to build an agent that can answer questions and help you make better business decisions.
Building a conversational search interface for your content using AI allows your users to ask specific questions and get direct answers.
Try out the Gemini API and our state of the art models, Gemini 1.5 Flash and 1.5 Pro.