# Missing Reserved PTUs for Steady-State Azure OpenAI Workloads

Canonical: https://www.pointfive.co/efficiency-hub/inefficiencies/missing-reserved-ptus-for-steady-state-azure-openai-workloads-f78d4

[Cloud Efficiency Hub](https://www.pointfive.co/efficiency-hub) 

# Missing Reserved PTUs for Steady-State Azure OpenAI Workloads

## Explanation

Many production Azure OpenAI workloads-such as chatbots, inference services, and retrieval-augmented generation (RAG) pipelines-use PTUs consistently throughout the day. When usage stabilizes after initial experimentation, continuing to rely on on-demand PTUs results in ongoing unnecessary spend. These workloads are strong candidates for reserved PTUs, which provide identical performance guarantees at a substantially reduced hourly rate. Migrating to reservations usually requires no architectural changes and delivers immediate cost savings.

## Relevant Billing Model

PTUs are billed hourly based on provisioned throughput. On-demand PTUs use standard hourly rates, whereas reserved PTUs offer significant discounts-often up to \\~80%-when capacity is committed for a month or year. Workloads running continuously on on-demand PTUs incur avoidable premium pricing.

## Detection

- Review PTU deployments supporting production workloads that operate continuously throughout the day

- Assess whether throughput demand remains stable enough to justify reserved capacity

- Identify deployments that have moved beyond experimentation but still use on-demand PTUs

- Evaluate the cost difference between on-demand PTUs and reserved PTUs for these workloads

## Remediation

- Purchase monthly or annual reserved PTUs for workloads with sustained, predictable throughput needs

- Establish governance criteria defining when production PTU deployments should transition to reservations

- Periodically reassess workload stability to ensure PTU reservation commitments remain aligned with demand

- Use cost modeling to evaluate reservation options as part of production readiness reviews

## Relevant Documentation

- [https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/provisioned-throughput](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/provisioned-throughput)

[Submit Feedback](https://hub.pointfive.co/inefficiencies/missing-reserved-ptus-for-steady-state-azure-openai-workloads-f78d4)

## At a glance

Reference

CER-0246

Cloud provider

Azure

Service

Azure Cognitive Services

Category

[AI](https://www.pointfive.co/efficiency-hub/service-category/ai)

Inefficiency type

Unoptimized Pricing Model

## Contributed by

- Ariel Lichterman 

### Ariel Lichterman

Cloud Researcher @ PointFive

[LinkedIn](https://www.linkedin.com/in/ariel-fishman-lichterman-01a096214/)

---
Source: the public page above. Product screenshots and illustrative interfaces are examples, not live customer data.