thinQmaster Virtual testing partner Adaptive practice exams that find your weak spots and drill them. Every answer explained. From $69
Enroll

thinQmaster

Find your exam

Five questions free, before you decide.

Step 1 · choose a vendor

In one of our camps? Your practice exams come with the tuition — they are on your study page already.

AI & Machine Learning · Intermediate

Provisioned Throughput

Reserved model inference capacity purchased for consistent performance, rather than paying per token on demand.

Definition

Amazon Bedrock Provisioned Throughput, Azure OpenAI provisioned throughput units (PTUs) and Vertex AI Provisioned Throughput guarantee capacity for predictable, high-volume workloads. Some Bedrock custom models require it.

Exam tip

Steady, high-volume, latency-sensitive traffic favors provisioned throughput; spiky or low traffic favors on-demand.

Related terms