AI glossary · Building and running AI
API
An API (application programming interface) lets one program use another’s features. AI companies offer APIs so developers can build their models into apps.
Also called application programming interface, AI API
In more detail
Instead of chatting in an app, a developer’s code sends a request, such as a prompt, to the AI provider and gets a completion back. Usage is usually billed per token.
Many AI tools you see in directories are built on top of these APIs, adding their own interface, prompt templates and features. Some are thin layers, often called AI wrappers.
Example
A note-taking app sends your meeting transcript to an AI model’s API and shows the returned summary.
Related terms
AI wrapperAn AI wrapper is an app built on top of someone else’s AI model, adding its own interface, prompts or workflow rather than its own model.TokenA token is a small chunk of text, often a word or part of a word, that a language model reads and writes. Usage limits and prices are counted in tokens.Function callingFunction calling lets an AI model ask an app to run a specific action, like checking the weather or searching a database, and then use the result in its reply.InferenceInference is when a trained AI model is used to produce an answer, such as a chatbot writing a reply, as opposed to the training stage when it learns.
Browse related tools
AI tools listed on BroUseAI in these categories.
