Skip to content
estudIA

AI glossary

API

An interface that lets one program talk to another. AI providers offer APIs so developers can use their models inside their own apps.

Through an AI API you send a request — the model name, your messages and settings — and get the response back as data. You pay per token used rather than a monthly subscription. APIs are how chatbots, automations and agents are built on top of models.

You need an API key to authenticate. Treat it like a password: never paste it into public code, forums or chats.

Example: An online shop sends each new review to a model’s API with the instruction “classify this review as positive, negative or mixed” and stores the answer in its database, without anyone opening a chat.

In practice

  • Chat and API are paid for separately: a ChatGPT or Claude subscription does not include API usage.
  • Check the prices per million tokens in our model comparison and set a spending limit.
  • If you do not code, no-code tools let you use the API from a visual editor.

Try it with the no-code automation tutorial.

Related terms

Learn more

← Back to the glossary