# Rate limit

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: rate limits, rate limited, rate limiting, usage limit, usage limits, quota, throttling, too many requests

A cap on how many requests or [tokens](https://ecosystem.samcarlton.com/token) an account can send to an [API](https://ecosystem.samcarlton.com/terms/api) in a set period. Requests over the cap fail with an error until capacity frees up.

**For example:** A product goes viral and sends ten times its usual requests to a [model provider](https://ecosystem.samcarlton.com/model-provider). The provider starts refusing some of them, and users see errors until the team asks for a higher limit.

## Connects to (5)

- [API](https://ecosystem.samcarlton.com/terms/api): Application programming interface.
- [Token](https://ecosystem.samcarlton.com/token): In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.
- [Usage-based pricing](https://ecosystem.samcarlton.com/usage-based-pricing): A way to charge where the bill follows how much the customer uses, instead of a flat fee.
- [Scaling](https://ecosystem.samcarlton.com/scaling): Adding capacity so a system can handle more use.
- [Model provider](https://ecosystem.samcarlton.com/model-provider): The company or service that runs an AI model and answers requests to it, usually over the internet through an API.

Map view: https://ecosystem.samcarlton.com/rate-limit