API (Application Programming Interface)
InfrastructureA software interface that allows developers to access AI model capabilities programmatically — the foundation of all AI-powered products.
Full Explanation
AI APIs let developers build applications on top of powerful models without training their own. You send a request (with your prompt and API key) and receive the model's response. OpenAI, Anthropic, Google, and Mistral all offer commercial APIs. Pricing is typically per million input/output tokens. Rate limits prevent overuse.
Related Terms
The basic unit of text that AI language models process — roughly equivalent to 3/4 of a word in English.
The process of running a trained AI model to generate outputs — what happens when you use an AI tool.
Constraints imposed by AI API providers on how many requests or tokens a user can process per minute, hour, or day.