google-gemini /cookbook
Examples and guides for using the Gemini API
★ 17,944⑂ 2,835👁 213⑃ 1,157● 347▤ 0
More from this author
+4
Daily
17,944
stars
2,835
forks
213
watchers
1,157
prs
347
issues
0
releases
README
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.
For Gemma quickstarts and examples, check out the Gemma cookbook.
---
Gemini 4 Hydrogen, Carbon & Argon: Start with Gemini 4 Hydrogen (gemini-4-hydrogen), the new default Gemini 4 model available on both the free and paid tiers for fast everyday coding, multimodal workflows, and tool-using agents (with four thinking levels up to xhigh), alongside Gemini 4 Carbon (gemini-4-carbon) for maximum reasoning depth and Gemini 4 Argon (gemini-4-argon) for fast frontier reasoning—all featuring a unified 1M context window and long decode up to 1M output tokens. Explore the Get Started and Thinking guides, including the migration guide.
Gemini 3.8 Flash: Our most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows. Get started with the Get Started and the thinking guides.
🎙️ Gemini 3.8 TTS & Custom Voices: Generate expressive single- and multi-speaker speech with Gemini 3.8 TTS , and design custom voices from text or replicate voices from audio with the new Voices guide !
Omni Flash: The Nano Banana of video editing is here! Learn how to call the model using the interactions API, edit videos with natural language and more here !
🍌 Nano-Banana 2.1: Go bananas with our latest image generation model: Nano-Banana 2.1. Get started here with 512px, thinking, search and image grounding, and a ton of examples!
🎶 Lyria 3.5: Channel your inner composer with Lyria 3.5. Get started here with full song generation, image-to-music, and a ton of examples!
Agents API: Create and run your custom agents using the new Antigravity agent !
Decisions API: Answer typed yes/no (noul), choice, and score questions with calibrated probabilities and zero output token cost. Get started with the Decisions API guide !
---
Navigating the Cookbook
This cookbook is organized into two main categories:
1. Quick Starts: Step-by-step guides covering both introductory topics ("Get Started ") and specific API features.
2. 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:
Gemini 4 Hydrogen: The fast, cost-efficient daily driver in the Gemini 4 series—available on both the free and paid tiers with a unified 1M context window, long decode continuation up to 1M output tokens, and thinking levels up to xhigh (gemini-4-hydrogen is now the default across Cookbook quickstarts). Start building in the Get Started guide .
Decisions API: Answer typed yes/no (noul), choice, and score questions with calibrated probabilities and zero output token cost usingTop issues
#1339[Bug] INVALID_ARGUMENT error when switching from Nano Banana 2 to Gemini 3.7 Flash4 comments · 2026-08-22#1389Support `excludeDomains` for `google_search` grounding in the Gemini Developer API (currently Vertex/Enterprise only)3 comments · 2026-09-23#1480`client.webhooks.create` wrapper in the `google-genai` Python SDK returns a `404 Not Found` error1 comments · 2026-11-08#1571What fast events does Gemini miss between video frames?0 comments · 2026-11-15#1570Evaluate when Gemini should flag a satellite image for human review0 comments · 2026-11-14#1569Example proposal: sourced web data tables with a remote MCP server (SpecStream) and the Interactions API0 comments · 2026-11-14