Skip to content
AI for Beginners

API(API)

A way for two pieces of software to talk to each other directly, so one program can use another's features without a person clicking around. It is like a serving hatch through which one system passes requests and receives answers. This software-to-software connection is called an API, short for application programming interface.

Most of the time you use AI through a website or app, typing into a box and reading the reply. An API is a different door into the same capability, one meant for other software rather than for a person. Through an API, a program can send a request to an AI and get an answer back automatically, with no one clicking anything.

The serving-hatch image is a useful one. In a busy kitchen, orders go in through the hatch and finished plates come back out, without the diners ever entering the kitchen. An API works the same way. One program passes a request through the hatch, the AI does the work, and the result comes back. The full name is application programming interface, though almost everyone says API.

Why should a beginner care? Because APIs are how AI gets woven into the tools you already use. When your email app suggests a reply, or a spreadsheet gains a summarise button, an API to a large language model is often quietly doing the work behind the scenes.

You do not need to use an API yourself to benefit from one. If you ever do go further, you will find that settings such as temperature and the choice of model become yours to control, including options like an open-source model or even local AI running on your own machine.

Related terms