# Tokens per Minute (TPM)

> A cap on how many tokens an app may use each minute. Over it, you wait.

**Field:** Artificial Intelligence  
**Category:** Cloud AI Platforms  
**Also known as:** Token Rate Limit, AI Rate Limit, Requests per Minute (AI), RPM

## Think of it like

It is like a tap that lets out only so much water each minute. The rest has to wait.

## Definition

Tokens per minute is a limit on how much text you can send to or get from an AI model each minute. Model services count it in tokens, the small pieces of text a model reads and writes. There is often a second limit on the number of requests per minute. When you go over either one, the service turns the request away with an error. Your app should wait a moment and try again. Bigger accounts can usually get higher limits.

## Example

Jack's app sends a burst of long chats to the Claude API. It passes its input tokens per minute limit and gets error 429, so the app waits and tries again.

## Why it matters

A busy app hits this wall first. Knowing the limit lets you plan for peaks instead of failing at them.

## Common mistake

Retrying at once in a tight loop. The new requests also fail and keep the app over the limit.

## Three principles

- **Counted in tokens.** Plus a cap on requests each minute.
- **Over means wait.** Error 429, then try again later.
- **Grows with the account.** Higher tiers get higher limits.

## Related terms

- [Token (AI)](https://learn.benibix.com/term/ai/token)
- [Rate Limiting](https://learn.benibix.com/term/development/rate-limiting)
- [Provisioned Throughput](https://learn.benibix.com/term/ai/provisioned-throughput)
- [Model as a Service (MaaS)](https://learn.benibix.com/term/ai/model-as-a-service)
- [Prompt Caching](https://learn.benibix.com/term/ai/prompt-caching)

## Told apart from

- [Tokens per Minute vs Provisioned Throughput](https://learn.benibix.com/compare/tokens-per-minute-vs-provisioned-throughput): People think provisioned throughput is just a higher tokens per minute limit, and it is not. A tokens per minute limit is a cap on shared capacity, and you pay only for what you use. Provisioned throughput is capacity set aside for you alone. You pay for it by the hour or month, even on quiet days. One is a ceiling. The other is a room you rent.

![Three panels. Left: a meter of tokens used this minute with a limit line, and a request over the line turned away with error 429. Middle: a prompt goes to a model and an answer comes back, while a storage box beside them is crossed out. Right: a photo, a sound clip and a sentence each go into a ready-made service and come out as labels, text and another language.](https://learn.benibix.com/diagrams/ai7-cloud-ai-rules.svg)

---

Source: https://learn.benibix.com/term/ai/tokens-per-minute
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
