Merge pull request #5340 from MicrosoftDocs/release-preview-ptu

[Out of Band Publish] release-preview-ptu -> main -- 06/04 - 01:00 PM PT

Author: Albertyang0

articles/ai-foundry/toc.yml

@@ -595,12 +595,25 @@ items:
     - name: Plan and manage costs for AI Foundry resources
       href: how-to/costs-plan-manage.md
       displayName: pricing, budget, estimate
-    - name: Manage quotas and limits for Foundry Models
-      href: ../ai-foundry/model-inference/quotas-limits.md?context=/azure/ai-foundry/context/context
     - name: Manage quotas
       href: how-to/quota.md
     - name: Increase rate limit
       href: how-to/autoscale.md
+  - name: Cost management for Foundry Models
+    items:
+    - name: Manage quotas and limits for Foundry Models
+      href: ../ai-foundry/model-inference/quotas-limits.md?context=/azure/ai-foundry/context/context
+    - name: What is the Provisioned Throughput offering (PTU)?
+      href: ../ai-services/openai/concepts/provisioned-throughput.md?context=/azure/ai-foundry/context/context
+      displayName: PTU, provisioned, provisioned throughput units
+    - name: Understanding and calculating PTU costs 
+      href: ../ai-services/openai/how-to/provisioned-throughput-onboarding.md?context=/azure/ai-foundry/context/context
+      displayName: PTU, provisioned, provisioned throughput units
+    - name: Get started with Provisioned Deployments
+      href: ../ai-services/openai/how-to/provisioned-get-started.md?context=/azure/ai-foundry/context/context
+      displayName: PTU, provisioned, provisioned throughput units
+    - name: Provisioned spillover
+      href: ../ai-services/openai/how-to/spillover-traffic-management.md?context=/azure/ai-foundry/context/context
 - name: Security & Governance
   items:
   - name: Identity & access management

articles/ai-services/openai/concepts/gov-provisioned.md

@@ -6,7 +6,7 @@ author: challenp
 ms.service: azure-ai-openai
 ms.topic: how-to
 ms.custom: references_regions, azuregovernment
-ms.date: 5/1/2025
+ms.date: 05/30/2025
 recommendations: false
 ---
 
@@ -84,7 +84,7 @@ In addition to the updates for the hourly payment model, new [Azure Reservations
 
 #### Supported models on commitment payment model:
 
-Only the following list of Azure OpenAI models are supported in Commitments. For onboarding any other models that aren't in the list below, or any newer models on provisioned throughput offering, refer to the [Azure OpenAI provisioned onboarding guide](../how-to/provisioned-throughput-onboarding.md) and [Azure Reservations for Azure OpenAI provisioned deployments](../how-to/provisioned-throughput-onboarding.md#azure-reservations-for-azure-openai-provisioned-deployments)
+Only the following list of Azure OpenAI models are supported in Commitments. For onboarding any other models that aren't in the list below, or any newer models on provisioned throughput offering, refer to the [Azure OpenAI provisioned onboarding guide](../how-to/provisioned-throughput-onboarding.md) and [Azure Reservations for Azure OpenAI provisioned deployments](../how-to/provisioned-throughput-onboarding.md#azure-reservations-for-azure-ai-foundry-provisioned-throughput)
 
 |Supported models on Commitment plan |Versions|
 |-|-|

articles/ai-services/openai/concepts/provisioned-migration.md

@@ -7,7 +7,7 @@ ms.service: azure-ai-openai
 ms.custom:
   - ignite-2024
 ms.topic: how-to
-ms.date: 03/26/2025
+ms.date: 05/30/2025
 author: aahill
 ms.author: aahi
 recommendations: false
@@ -44,7 +44,7 @@ This article is intended for existing users of the provisioned throughput offeri
 | Default provisioned-managed quota in many regions | Get started quickly in new regions without having to first request quota. |
 | Flexible choice of payment model for existing provisioned customers | Customers with commitments can stay on the commitment model until the end of life of the currently supported models, and can choose to migrate existing commitments to hourly/reservations via managed process. We recommend migrating to hourly/ reservations to take advantage of term discounts and to work with the latest models. |
 | Supports latest model generations | The latest models are available only on hourly/ reservations in provisioned offering. |
-| Differentiated pricing | Greater flexibility and control of pricing and performance. In December 2024, we introduced  differentiated hourly pricing across [global provisioned](../how-to/deployment-types.md#global-provisioned), [data zone provisioned](../how-to/deployment-types.md#data-zone-provisioned), and [provisioned](../how-to/deployment-types.md#provisioned) deployment types with the option to purchase [Azure Reservations](#new-azure-reservations-for-global-and-data-zone-provisioned-deployments) to support additional discounts. For more information on the hourly price for each provisioned deployment type, see the [Pricing details](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) page. |
+| Differentiated pricing | Greater flexibility and control of pricing and performance. In December 2024, we introduced  differentiated hourly pricing across [global provisioned](../how-to/deployment-types.md#global-provisioned), [data zone provisioned](../how-to/deployment-types.md#data-zone-provisioned), and [regional provisioned](../how-to/deployment-types.md#regional-provisioned) deployment types with the option to purchase [Azure Reservations](#new-azure-reservations-for-global-and-data-zone-provisioned-deployments) to support additional discounts. For more information on the hourly price for each provisioned deployment type, see the [Pricing details](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/) page. |
 
 ## Usability improvement details
 
@@ -81,7 +81,7 @@ We also recommend that customers using commitments now create their deployments
 See the following links for more information. The guidance for reservations and commitments is the same:
 
 * [Capacity Transparency](#self-service-migration)
-* [Sizing reservations](../how-to/provisioned-throughput-onboarding.md#important-sizing-azure-openai-provisioned-reservations)
+* [Sizing reservations](../how-to/provisioned-throughput-onboarding.md#important-sizing-azure-ai-foundry-provisioned-throughput-reservation)
 
 ## New hourly reservation payment model
 
@@ -112,7 +112,7 @@ In addition to the updates for the hourly payment model, in December 2024 new [A
 - Commitments can't be canceled or altered during their term, except to add new PTUs.
 
 #### Supported models on commitment payment model:
-  Only the following list of Azure OpenAI models are supported in Commitments. For onboarding any other models that aren't in the list below, or any newer models on provisioned throughput offering,  refer to the [Azure OpenAI provisioned onboarding guide](../how-to/provisioned-throughput-onboarding.md) and [Azure Reservations for Azure OpenAI provisioned deployments](../how-to/provisioned-throughput-onboarding.md#azure-reservations-for-azure-openai-provisioned-deployments)
+  Only the following list of Azure OpenAI models are supported in Commitments. For onboarding any other models that aren't in the list below, or any newer models on provisioned throughput offering,  refer to the [Azure OpenAI provisioned onboarding guide](../how-to/provisioned-throughput-onboarding.md) and [Azure Reservations for Azure OpenAI provisioned deployments](../how-to/provisioned-throughput-onboarding.md#azure-reservations-for-azure-ai-foundry-provisioned-throughput)
 
 |Supported models on Commitment plan |Versions|
 |-|-|