API
Application Programming Interface — a defined way for one software application to request data or actions from another, enabling tools to communicate without a human in the loop.
An API (Application Programming Interface) is a set of rules that lets two software applications talk to each other. When you connect Zapier to Gmail, or when your app calls OpenAI to generate text, those connections work through APIs.
How it works: The requesting application sends an HTTP request to an API endpoint (a URL), usually with authentication credentials and parameters. The server processes the request and returns a response — typically in JSON format.
Key concepts: - Endpoint: The specific URL you call — e.g., `api.openai.com/v1/chat/completions` - API key: A credential that proves you're authorised to use the service - Rate limit: The maximum number of calls allowed in a given time period - Payload: The data you send with the request (your prompt, parameters, etc.)
Why APIs matter for AI builders: Every major AI tool — Claude, ChatGPT, ElevenLabs, Stable Diffusion — offers an API. Calling an API from your own code means you control the experience: your UI, your workflow, your brand. No-code tools like Zapier and Make.com connect APIs without writing code.
Pricing: AI API calls are charged per token, per image, or per second of audio. Costs compound at scale — which is why on-device models with zero API cost are strategically significant.
Example
You build a Chrome extension that highlights selected text and rewrites it using Claude. When the user clicks the button, your extension calls the Anthropic API with the selected text as the prompt. Claude returns the rewritten version and your extension swaps it in — all in under a second.
Related terms
Webhook
A way for one application to automatically notify another when something happens, by sending an HTTP request to a URL you specify.
Automation
Using software to perform tasks without human intervention — triggered by an event, running on a schedule, or responding to conditions.
Token
The smallest unit of text an AI processes—usually a word fragment, character, or subword.
Inference
The process of a trained model generating a response to an input. When you chat with ChatGPT, that's inference.
No-Code
Software tools that let non-programmers build apps, automations, and workflows using visual interfaces instead of writing code.