ModelRefs / Requests Per Minute (RPM) — AI Glossary
Requests Per Minute (RPM) — AI Glossary
An API rate limit specifying the maximum number of API calls a caller can make per minute, independent of token count. Also called RPM or request rate limit.
Overview
RPM limits protect against request-flood patterns regardless of token volume. Both TPM and RPM limits may bind independently. Chatbot applications with many short messages hit RPM limits; document processing with long contexts hits TPM first. Design for both: queue-based dispatch with per-second smoothing.
Reference details
| Topic | ecosystem |
|---|---|
| Also known as | RPM, request rate limit |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Requests Per Minute (RPM) — AI Glossary.
Frequently asked questions
What is Requests Per Minute (RPM)?
An API rate limit specifying the maximum number of API calls a caller can make per minute, independent of token count.
Is Requests Per Minute (RPM) the same as RPM?
Yes — RPM, request rate limit are common aliases for Requests Per Minute (RPM).
What concepts are related to Requests Per Minute (RPM)?
Closely related concepts include tokens per minute, rate limiting, retry with backoff.