What an API Actually Is

An API (application programming interface) is a defined way for one piece of software to ask another piece of software to do something, and get a result back — without a human clicking any buttons in between. An AI API specifically lets your own code send a request to an AI model and receive its response directly, programmatically.

This is a genuinely different way of using the same underlying AI model compared to a chat app. In a chat app, a human types a message and reads the reply on screen. Through an API, your own program sends the request and decides what to do with the response — show it to a user, save it somewhere, feed it into another step of a larger process, anything code can do.

Using an AI model this way usually costs money based on actual usage, billed per request rather than a flat monthly subscription like a consumer chat app might use — worth knowing before building something that could send a very large number of requests.

What does using an AI model "via API" actually mean?

A defined way for one piece of software to request something from another piece of software is called a(n) ____.

Using an AI API is typically billed per request/usage, rather than a single flat subscription price.