← Back to the AI Glossary 📖 Infrastructure & Ops

API (Application Programming Interface)

A defined way for one piece of software to talk to another — in AI, it's how developers send a prompt to a model and get a response back programmatically, without using a chat app.

Every AI-powered app or tool you use that isn't the AI company's own chat interface is almost certainly built by calling their API behind the scenes.
One of 60 free AI glossary terms
Plain-language definitions for the AI jargon you'll actually run into — no email needed, ever, for this section.
Browse the Full Glossary →
More in Infrastructure & Ops
Rate Limit
A cap on how many requests (or how much usage) an account can make to an AI service within...
Latency
The delay between sending a request to an AI model and receiving a response — lower latenc...
Prompt Caching
A technique where an AI provider temporarily stores parts of a prompt it has seen before,...
Cold Start
The extra delay before an AI system responds to its very first request in a while, as oppo...