Send your first prompt to a live LLM API

Every tutorial uses a different SDK and I just want one call that actually works.

BeginnerRead 5 minDoing: 20 minutes6 steps

▶ Start

What you'll have at the end

A script that sends one prompt and prints the model's reply, key read from the environment.

Before you start

You need

A computer where you can run a short script, and access to a language-model provider's developer console for creating an account.

Not covered

Streaming the reply as it arrives, retrying a failed request, and remembering earlier turns of a conversation are separate pieces this script leaves alone.

Leans on

Get your credentials in place

Create an account and a key
Keep the key out of your script

Wire the client to your key

Install the official client library
Point a client at your key

Send it and read the reply

Send one prompt and capture the reply
Pull out the text and print it

Where to go next

Get your API key off GitHub

You already committed a key to a file or a public repository and need to contain that leak right now.

Replies arrive all at once instead of streaming token by token

You want this same kind of call to print its answer piece by piece as it arrives.

Checked 15 Aug 2026

Part of the LLM APIs and Integration cookbook