The Gemini API and your first script

The concept

Google serves Gemini through an API with a generous free tier for experimentation, native handling of images and audio, and an SDK for Python and Node. The idea is simple: the same model you have been chatting with also answers a web request, so you can put it inside a script, a spreadsheet or a page. A key identifies you; a request sends the text; a response comes back as data.

The reason to try it once, even if you never build anything: it makes the chat version less mysterious. You see that the whole conversation is text in and text out, that your instructions are literally lines of a request, and that "the model" is one parameter among several.

A first call looks like this:

from google import genai

client = genai.Client()      # reads GEMINI_API_KEY

r = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Explain what a data analyst does in three concrete sentences.",
)

print(r.text)