Welcome to the Gemini API Cookbook

This cookbook provides a structured learning path for using the Gemini API, focusing on hands-on tutorials and practical examples. For comprehensive API documentation, visit ai.google.dev.

---

Gemini 3: For the most recent updates on our latest generation, please check the Get Started and the thinking guides who include migration guides.

> 🍌 Nano-Banana Pro: Go bananas with our new flagship image generation model with thinking and search grounding and 4K image generation. Get started here with a ton of examples!

---

Navigating the Cookbook

This cookbook is organized into two main categories:

• Quick Starts: Step-by-step guides covering both introductory topics ("Get Started ") and specific API features.

• Examples: Practical use cases demonstrating how to combine multiple features.

We also showcase Demos in separate repositories, illustrating end-to-end applications of the Gemini API.

What's New?

Here are the recent additions and updates to the Gemini API and the Cookbook:

• 🍌 Nano-banana Pro: Use Gemini's native image generation capabilities to edit images with high consistency or generate visual stories. Now with thinking, search grounding and 4K output!

• File Search: Discover how to ground generations in your own data in a hosted RAG system with the File Search quickstart .

• Grounding with Google Maps: Get started using factual geographical data from 📍 Google Maps in your apps! See the Google Maps section of the Grounding Guide .

• Veo 3.1: Get started with our video generation model with this Veo guide, including image-to-videos and video extension!

• Gemini Robotics-ER 1.5: Learn about this new Gemini model specifically for spatial understanding and reasoning for robotics applications.

• Lyria and TTS: Get started with podcast and music generation with the TTS and Lyria RealTime models.

• LiveAPI: Get started with the multimodal Live API and unlock new interactivity with Gemini.

• Recently Added Guides:

• Grounding : Discover different ways to ground Gemini's answer using different tools, from Google Search to Youtube and URLs and the new Maps grounding tool.

• Batch API : Use Batch API to send large volume of non-time-sensitive requests to the model and get up to 90% discount.

• Logs and datasets : Process and evaluate your collected logs using the Batch API.

1. Quick Starts

The quickstarts section contains step-by-step tutorials to get you started with Gemini and learn about its specific features. To begin, you'll need:

• A Google account.

• An API key (create one in Google AI Studio).

We recommend starting with the following:

• Authentication : Set up your API key for access.

• Get started : Get started with Gemini models and the Gemini API, covering basic prompting and multimodal input.

Then, explore the other quickstarts tutorials to learn about individual features:

• Get started with Live API : Get started with the live API with this comprehensive overview of its capabilities

• Get started with Veo : Get started with our video generation capabilities

• Get started with Imagen and Native image generation : Get started with our image generation capabilities

• Grounding : use Google Search for grounded responses

• Code execution : Generate and run Python code to solve complex tasks and even output graphs

• And many more

2. Examples (Practical Use Cases)

These examples demonstrate how to combine multiple Gemini API features or 3rd-party tools to build more complex applications.

• Browser as a tool : Use a web browser for live and internal (intranet) web interactions

• Illustrate a book : Use Gemini to create illustration for an open-source book

• Animated Story Generation : Create animated videos by combining Gemini's story generation, Imagen, and audio synthesis

Plotting and mapping Live : Mix Live API and Code execution* to solve complex tasks live 3D Spatial understanding : Use Gemini 3D spatial* abilities to understand 3D scenes Gradio and live API: Use gradio to deploy your own instance of the Live API*

• And many many more

3. Demos (End-to-End Applications)

These fully functional, end-to-end applications showcase the power of Gemini in real-world scenarios.

• Gemini CLI: Open-source AI agent that brings the power of Gemini directly into your terminal

• Gemini API quickstart: Python Flask App running with the Google AI Gemini API, designed to get you started building with Gemini's multi-modal capabilities

• Multimodal Live API Web Console: React-based starter app for using the Multimodal Live API over a websocket

• Fullstack Langgraph Quickstart: A fullstack application using a React frontend and a LangGraph-powered backend agent

• Google AI Studio Starter Applets: A collection of small apps that demonstrate how Gemini can be used to create interactive experiences

Official SDKs

The Gemini API is a REST API. You can call it directly using tools like curl (see REST examples or the great Postman workspace), or use one of our official SDKs:

• Python

• Go

• Node.js

• Dart (Flutter)

• Android

• Swift

Get Help

Ask a question on the Google AI Developer Forum.

The Gemini API on Google Cloud Vertex AI

For enterprise developers, the Gemini API is also available on Google Cloud Vertex AI. See this repo for examples.

Contributing

Contributions are welcome! See CONTRIBUTING.md for details. Thank you for developing with the Gemini API! We're excited to see what you create.