# Always-on PTUs for seasonal or cyclical Azure OpenAI workloads Canonical: https://www.pointfive.co/efficiency-hub/inefficiencies/always-on-ptus-for-seasonal-or-cyclical-azure-openai-workloads-ccb97 Many Azure OpenAI workloads - such as reporting pipelines, marketing workflows, batch inference jobs, or time-bound customer interactions-only run... By: Ariel Fishman-Lichterman Updated: 2026-09-28 [Cloud Efficiency Hub](https://www.pointfive.co/efficiency-hub) # Always-On PTUs for Seasonal or Cyclical Azure OpenAI Workloads The short version Many Azure OpenAI workloads - such as reporting pipelines, marketing workflows, batch inference jobs, or time-bound customer interactions-only run during specific periods. [Ariel Fishman-Lichterman](https://www.linkedin.com/in/ariel-fishman-lichterman-01a096214/) Cloud Researcher @ PointFive Azure service [Azure Cognitive Services](https://www.pointfive.co/efficiency-hub/cloud-services/azure-cognitive-services) Category [AI](https://www.pointfive.co/efficiency-hub/service-category/ai) Reference CER-0238 Type Idle or Unused Resource ## Explanation Why the waste happens and who it affects. When PTUs remain fully provisioned 24/7, organizations incur continuous fixed cost even during extended idle time. Although Azure does not offer native PTU scheduling, teams can use automation to provision and deprovision PTUs based on predictable cycles. This allows them to retain performance during peak windows while reducing cost during low-activity periods. ## Billing model The pricing dimensions that drive this cost. On hourly billing, PTUs are charged for as long as the deployment exists, prorated to the minute (deployments cannot be paused), while Azure Reservations cover a fixed PTU quantity at a discount for sustained use. If workloads operate on weekly, monthly, or seasonal cycles, keeping PTUs active outside of demand windows results in paying for idle dedicated capacity. ## How to detect 4 checks to find it in your estate. - Identify PTU-backed workloads with recurring or predictable activity patterns - Review utilization trends showing regular periods of inactivity despite continuous PTU allocation - Evaluate whether workload timing aligns with business cycles, reporting schedules, or seasonal events - Assess whether PTUs remain active during nights, weekends, or large idle blocks ## How to fix 5 ways to remove the waste. - Use automation to scale PTUs up and down according to expected workload schedules - Reserve scheduling for short, predictable demand windows: Microsoft advises against scaling production deployments up and down on hourly billing, because a right-sized reservation is typically cheaper for sustained production use and scaling down releases capacity that may not be available when you scale back up - Provision PTUs only during windows where predictable throughput and low latency are required - Establish scheduling policies for cyclical workloads to prevent unnecessary continuous provisioning - Regularly re-evaluate patterns to ensure scheduling aligns with evolving business cycles ## Documentation Vendor references for pricing and configuration. - [Provisioned throughput billing and cost management - Microsoft Foundry learn.microsoft.com](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput-billing) - [Provisioned throughput for Foundry Models - Microsoft Foundry learn.microsoft.com](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/provisioned-throughput) - [Azure OpenAI Service - Pricing azure.microsoft.com](https://azure.microsoft.com/en-us/pricing/details/azure-openai/) ## Related inefficiencies [Browse the library](https://www.pointfive.co/efficiency-hub) - Azure Cognitive Services CER-0561 ### [Low-Traffic Fine-Tuned Azure OpenAI Deployments Accruing Hosting Fees](https://www.pointfive.co/efficiency-hub/inefficiencies/low-traffic-fine-tuned-azure-openai-deployments-accruing-hosting-fees) A fine-tuned Azure OpenAI model deployed as Standard or Global Standard carries an hourly hosting fee on top of per-token inference, and Microsoft states that the fee applies whether or not any chat completions or Responses API calls are... AI - Azure Cognitive Services CER-0248 ### [Non-Production Azure OpenAI Deployments Using PTUs Instead of PAYG](https://www.pointfive.co/efficiency-hub/inefficiencies/non-production-azure-openai-deployments-using-ptus-instead-of-payg-9fe81) Development, testing, QA, and sandbox environments rarely have the steady, predictable traffic patterns needed to justify PTU deployments. These workloads often run intermittently, with lower throughput and shorter usage windows. When PTUs... AI - Azure Cognitive Services CER-0266 ### [Underutilized PTU Quota for Azure OpenAI Deployments](https://www.pointfive.co/efficiency-hub/inefficiencies/underutilized-ptu-quota-for-azure-openai-deployments-da831) When organizations size PTU capacity based on peak expectations or early traffic projections, they often end up with more throughput than regularly required. If real-world usage plateaus below provisioned levels, a portion of the PTU... AI --- Source: the public page above. Product screenshots and illustrative interfaces are examples, not live customer data.