# Provisioned Throughput

> You rent a fixed share of a model, for a fixed price.

**Field:** Artificial Intelligence  
**Category:** Cloud AI Platforms  
**Also known as:** Reserved Capacity, Provisioned Throughput Units, PTU

## Think of it like

It is like renting your own car for a month. It is always ready, even on days you stay home.

## Definition

Provisioned throughput means you reserve a fixed amount of model capacity from a cloud, for a fixed price. You pay by the hour or the month, whether you use it or not. In return, your requests do not share space with everyone else, so speed stays steady. Each cloud has its own name and unit for it. It suits apps with steady, heavy traffic. For light or spiky use, paying per token is usually cheaper.

## Example

Emma's help app gets thousands of chats each hour, all day. She buys provisioned throughput, so replies stay fast at the busiest times.

## Why it matters

For a busy app, steady speed and a known bill can count for more than the lowest price.

## Common mistake

Buying it before you know your traffic. If the capacity sits idle, you pay for nothing.

## Three principles

- **Reserved for you.** Not shared.
- **Fixed price.** Used or not.
- **Steady speed.** For heavy traffic.

## Related terms

- [Model as a Service (MaaS)](https://learn.benibix.com/term/ai/model-as-a-service)
- [Token Pricing](https://learn.benibix.com/term/development/token-pricing)
- [Model Serving](https://learn.benibix.com/term/ai/model-serving)
- [Amazon Bedrock](https://learn.benibix.com/term/ai/amazon-bedrock)
- [Tokens per Minute (TPM)](https://learn.benibix.com/term/ai/tokens-per-minute)

## Told apart from

- [Model as a Service vs Provisioned Throughput](https://learn.benibix.com/compare/model-as-a-service-vs-provisioned-throughput): People often think provisioned throughput is just a faster, pricier kind of paying per token. It is a different deal. With model as a service, you share space and pay for each token. With provisioned throughput, you rent a fixed slice. You pay the same whether you use it or not, and get steady speed. Light or spiky use is cheaper per token. Heavy, steady use can be cheaper to reserve.
- [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.

![Two bills over a month. Pay per token goes up and down with use. Provisioned throughput is a flat line, paid even on quiet days.](https://learn.benibix.com/diagrams/ca-provisioned-throughput.svg)

---

Source: https://learn.benibix.com/term/ai/provisioned-throughput
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.
