Vocabulary · Volume 1 and Volume 2

Provisioned throughput

Model-serving capacity held for a deployment and billed by the hour, busy or idle. The work it holds varies with the model and the prompt mix; quota permits it without holding it, and a reservation discounts it without guaranteeing it.

The definition appears in the Volume 1 glossary and Volume 2 glossary. This page collects where the book uses the term and where the blog takes it up.