Gemini API Basics - Keys, a First Request, Streaming and Errors
Get a Gemini API key, keep it safe, make a first request, stream a reply and handle the errors you are most likely to meet.
The Gemini API gives your software access to Google's models, including text and image understanding. A first call takes minutes. This guide covers that first call, plus the habits that keep your key and your budget safe once the code is doing real work.
Related guides
Getting Reliable JSON and Structured Output from AI
Techniques for making a model return clean JSON every time, from prompt wording and schemas to validation and retry loops in your code.
6 min read
Building Your First AI Agent, Step by Step
Understand what an agent is, then build a simple one: a goal, a loop, a few tools and clear stopping rules, with a framework-free Python sketch.
7 min read
Getting Started with Google Gemini
A practical first-day tour of Gemini: where to find it, what it is good at, how to prompt it, and what to check before using it with work data.
5 min read