Gemini 3.6 Flash

Models & AI Labs 💻 Jupyter Notebook ⚖️ Apache-2.0 🟢 Actively maintained
17.7k stars

The Gemini API Cookbook is a collection of Jupyter notebooks and examples for learning and building with Google's Gemini API. It provides hands-on tutorials for various features like image generation, video editing, and agents, aimed at developers who want to integrate Gemini into their applications.

✨ Key features

  • Step-by-step quickstarts for Gemini API features
  • Practical examples combining multiple API capabilities
  • Guides for image, video, and music generation
  • Tutorials for Live API, grounding, and batch processing
  • Official SDKs for Python, Go, Node.js, Java, C#

🎯 Use cases

  • Build conversational video editing apps with Omni Flash
  • Generate and edit images with Nano-Banana models
  • Create custom agents using the Agents API
  • Transcribe audio with word-level timestamps and diarization
  • Ground responses with Google Search or Maps

📦 Installation

🧰 Requirements: Requires a Google account and an API key from Google AI Studio. No specific OS or runtime mentioned.

The README does not provide installation steps. It is a collection of notebooks and examples, so you can clone the repository and open the notebooks in Jupyter or Colab.

🚀 Usage

# Example from Get_started.ipynb (simplified)
import google.generativeai as genai

genai.configure(api_key='YOUR_API_KEY')
model = genai.GenerativeModel('gemini-3.8-flash')
response = model.generate_content('Hello')
print(response.text)

❓ FAQ

What do I need to get started?

You need a Google account and an API key from Google AI Studio.

What models are covered?

The cookbook covers Gemini 3.8 Flash, 3.5 Flash-Lite, Omni Flash, Nano-Banana 2, Lyria 3.5, and others.

Are there official SDKs?

Yes, official SDKs are available for Python, Go, Node.js, Java, and C#.

Where can I get help?

You can ask questions on the Google AI Developer Forum.

📊 Repository

Stars★ 17,748
Forks🍴 2,751
Open issues🐛 41
Last commit🕒 Sep 4, 2026
Created📅 Mar 2024
Language💻 Jupyter Notebook
License⚖️ Apache-2.0

🤖 Overview, features, install steps and FAQ were generated from the project's README on Sep 4, 2026. Always check the original source before running commands.