Update Azure AI Foundry and Azure AI services references

Author: JKirsch1

articles/api-management/amazon-bedrock-passthrough-llm-api.md

@@ -15,7 +15,7 @@ ms.custom: template-how-to, build-2024
 
 [!INCLUDE [api-management-availability-all-tiers](../../includes/api-management-availability-all-tiers.md)]
 
-In this article, you import an Amazon Bedrock language model API into your API Management instance as a passthrough API. This is an example of a model that's hosted on an inference provider other than Azure AI services. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
+In this article, you import an Amazon Bedrock language model API into your API Management instance as a passthrough API. This is an example of a model that's hosted on an inference provider other than Foundry Tools. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
 
 Learn more about managing AI APIs in API Management:
 

articles/api-management/api-management-authenticate-authorize-ai-apis.md

@@ -102,7 +102,7 @@ Follow these steps to configure your API Management instance to use a managed id
     ```
 
 > [!TIP]
-> Instead of using the `authentication-managed-identity` and `set-header` policies shown in this example, you can configure a [backend](backends.md) resource that directs API requests to the AI service endpoint. In the backend configuration, configure managed identity credentials to the `https://cognitiveservices.azure.com/` resource. Azure API Management automates these steps when you [import an API directly from Microsoft Foundry](azure-ai-foundry-api.md).  
+> Instead of using the `authentication-managed-identity` and `set-header` policies shown in this example, you can configure a [backend](backends.md) resource that directs API requests to the Azure AI Services endpoint. In the backend configuration, configure managed identity credentials to the `https://cognitiveservices.azure.com/` resource. Azure API Management automates these steps when you [import an API directly from Microsoft Foundry](azure-ai-foundry-api.md).  
 
 ## OAuth 2.0 authorization by using identity provider
 

articles/api-management/azure-ai-foundry-api.md

@@ -24,11 +24,11 @@ Learn more about managing AI APIs in API Management:
 
 ## Client compatibility options
 
-API Management supports two client compatibility options for AI APIs from Microsoft Foundry. When you import the API using the wizard, choose the option suitable for your model deployment. The option determines how clients call the API and how the API Management instance routes requests to the AI service.
+API Management supports two client compatibility options for AI APIs from Microsoft Foundry. When you import the API using the wizard, choose the option suitable for your model deployment. The option determines how clients call the API and how the API Management instance routes requests to the Foundry Tool.
 
 * **Azure OpenAI** - Manage Azure OpenAI in Microsoft Foundry model deployments. 
 
-    Clients call the deployment at an `/openai` endpoint such as `/openai/deployments/my-deployment/chat/completions`. Deployment name is passed in the request path. Use this option if your AI service only includes Azure OpenAI model deployments. 
+    Clients call the deployment at an `/openai` endpoint such as `/openai/deployments/my-deployment/chat/completions`. Deployment name is passed in the request path. Use this option if your Foundry Tool only includes Azure OpenAI model deployments. 
 
 * **Azure AI** - Manage model endpoints in Microsoft Foundry that are exposed through the [Azure AI Model Inference API](/azure/ai-studio/reference/reference-model-inference-api).
 
@@ -38,7 +38,7 @@ API Management supports two client compatibility options for AI APIs from Micros
 
 - An existing API Management instance. [Create one if you haven't already](get-started-create-service-instance.md).
 
-- An Azure AI service in your subscription with one or more models deployed. Examples include models deployed in Microsoft Foundry or Azure OpenAI.
+- A Foundry Tool in your subscription with one or more models deployed. Examples include models deployed in Microsoft Foundry or Azure OpenAI.
 
 ## Import Microsoft Foundry API using the portal
 
@@ -47,8 +47,8 @@ Use the following steps to import an AI API to API Management.
 When you import the API, API Management automatically configures:
 
 * Operations for each of the API's REST API endpoints
-* A system-assigned identity with the necessary permissions to access the AI service deployment.
-* A [backend](backends.md) resource and a [set-backend-service](set-backend-service-policy.md) policy that direct API requests to the AI service endpoint.
+* A system-assigned identity with the necessary permissions to access the Foundry Tool deployment.
+* A [backend](backends.md) resource and a [set-backend-service](set-backend-service-policy.md) policy that direct API requests to the Azure AI Services endpoint.
 * Authentication to the backend using the instance's system-assigned managed identity.
 * (optionally) Policies to help you monitor and manage the API.
 
@@ -59,10 +59,10 @@ To import a Microsoft Foundry API to API Management:
 1. Under **Create from Azure resource**, select **Microsoft Foundry**.
 
     :::image type="content" source="media/azure-ai-foundry-api/ai-foundry-api.png" alt-text="Screenshot of creating an OpenAI-compatible API in the portal." :::
-1. On the **Select AI service** tab:
-    1. Select the **Subscription** in which to search for AI services. To get information about the model deployments in a service, select the **deployments** link next to the service name.
+1. On the **Select AI Service** tab:
+    1. Select the **Subscription** in which to search for Foundry Tools. To get information about the model deployments in a service, select the **deployments** link next to the service name.
        :::image type="content" source="media/azure-ai-foundry-api/deployments.png" alt-text="Screenshot of deployments for an AI service in the portal.":::
-    1. Select an AI service. 
+    1. Select a Foundry Tool. 
     1. Select **Next**.
 1. On the **Configure API** tab:
     1. Enter a **Display name** and optional **Description** for the API.

articles/api-management/backends.md

@@ -28,7 +28,7 @@ For other APIs, such as APIs from Azure services, you import an Azure resource w
 
 API Management also supports using other resources as an API backend, such as:
 * A [Service Fabric cluster](how-to-configure-service-fabric-backend.yml).
-* AI services.
+* Foundry Tools.
 * A custom service.
 
 For these backends, you can create a *backend entity* in API Management and reference it in your APIs.  
@@ -51,7 +51,7 @@ You can configure and manage backend entities in the Azure portal, or by using A
 You can create a backend in the Azure portal, or by using Azure APIs or tools.
 
 > [!NOTE]
-> When you import certain APIs, such as APIs from Microsoft Foundry or other AI services, API Management automatically configures a backend entity.
+> When you import certain APIs, such as APIs from Microsoft Foundry or other Foundry Tools, API Management automatically configures a backend entity.
 
 To create a backend in the portal:
 

articles/api-management/breaking-changes/identity-provider-adal-retirement-sep-2025.md

@@ -23,7 +23,7 @@ This change will have no effect on the availability of your API Management servi
 
 Your service is impacted by this change if:
 
-* You've configured an [Microsoft Entra ID](../api-management-howto-aad.md) or [Azure AD B2C](../api-management-howto-aad-b2c.md) identity provider for user account authentication using the ADAL and use the provided developer portal.
+* You've configured a [Microsoft Entra ID](../api-management-howto-aad.md) or [Azure AD B2C](../api-management-howto-aad-b2c.md) identity provider for user account authentication using the ADAL and use the provided developer portal.
 
 ## What is the deadline for the change?
 

articles/api-management/edit-api.md

@@ -1,5 +1,5 @@
 ---
-title: Edit an API in the Azure Portal  | Microsoft Docs
+title: Edit an API in the Azure portal  | Microsoft Docs
 description: Learn how to use API Management to edit an API or its swagger.
 services: api-management
 author: dlepow

articles/api-management/front-door-api-management.md

@@ -143,7 +143,7 @@ The following are high level steps to add an endpoint for the developer portal t
 For more information and details about settings, see [How to configure an origin for Azure Front Door](../frontdoor/how-to-configure-origin.md#create-a-new-origin-group).
 
 > [!NOTE]
-> If you've configured an [Microsoft Entra ID](api-management-howto-aad.md) or [Microsoft Entra External ID](/entra/external-id/customers/overview-customers-ciam) identity provider for the developer portal, you need to update the corresponding app registration with an additional redirect URL to Front Door. In the app registration, add the URL for the developer portal endpoint configured in your Front Door profile.
+> If you've configured a [Microsoft Entra ID](api-management-howto-aad.md) or [Microsoft Entra External ID](/entra/external-id/customers/overview-customers-ciam) identity provider for the developer portal, you need to update the corresponding app registration with an additional redirect URL to Front Door. In the app registration, add the URL for the developer portal endpoint configured in your Front Door profile.
 
 ## Related content
 

articles/api-management/genai-gateway-capabilities.md

@@ -45,7 +45,7 @@ AI adoption in organizations involves several phases:
 
 As AI adoption matures, especially in larger enterprises, the AI gateway helps address key challenges. It helps you:
 
-* Authenticate and authorize access to AI services
+* Authenticate and authorize access to Foundry Tools
 * Load balance across multiple AI endpoints
 * Monitor and log AI interactions
 * Manage token usage and quotas across multiple applications
@@ -68,7 +68,7 @@ For example, to onboard a model deployed in Microsoft Foundry or another provide
 
 More information:
 
-* [Import an Microsoft Foundry API](azure-ai-foundry-api.md)
+* [Import a Microsoft Foundry API](azure-ai-foundry-api.md)
 * [Import a language model API](openai-compatible-llm-api.md)
 * [Expose a REST API as an MCP server](export-rest-mcp-server.md)
 * [Expose and govern an existing MCP server](expose-existing-mcp-server.md)
@@ -78,15 +78,15 @@ More information:
 
 One of the main resources in generative AI services is *tokens*. Microsoft Foundry and other providers assign quotas for your model deployments as tokens per minute (TPM). You distribute these tokens across your model consumers, such as different applications, developer teams, or departments within the company.
 
-If you have a single app connecting to an AI service backend, you can manage token consumption with a TPM limit that you set directly on the model deployment. However, when your application portfolio grows, you might have multiple apps calling single or multiple AI service endpoints. These endpoints can be pay-as-you-go or [Provisioned Throughput Units](/azure/ai-services/openai/concepts/provisioned-throughput) (PTU) instances. You need to make sure that one app doesn't use the whole TPM quota and block other apps from accessing the backends they need.
+If you have a single app connecting to an AI service backend, you can manage token consumption with a TPM limit that you set directly on the model deployment. However, when your application portfolio grows, you might have multiple apps calling single or multiple Azure AI Services endpoints. These endpoints can be pay-as-you-go or [Provisioned Throughput Units](/azure/ai-services/openai/concepts/provisioned-throughput) (PTU) instances. You need to make sure that one app doesn't use the whole TPM quota and block other apps from accessing the backends they need.
 
 ### Token rate limiting and quotas
 
-Configure a token limit policy on your LLM APIs to manage and enforce limits per API consumer based on the usage of AI service tokens. By using this policy, you can set a TPM limit or a token quota over a specified period, such as hourly, daily, weekly, monthly, or yearly. 
+Configure a token limit policy on your LLM APIs to manage and enforce limits per API consumer based on the usage of Foundry Tool tokens. By using this policy, you can set a TPM limit or a token quota over a specified period, such as hourly, daily, weekly, monthly, or yearly. 
 
 :::image type="content" source="media/genai-gateway-capabilities/token-rate-limiting.png" alt-text="Diagram of limiting Azure OpenAI Service tokens in API Management.":::
 
-This policy provides flexibility to assign token-based limits on any counter key, such as subscription key, originating IP address, or an arbitrary key defined through a policy expression. The policy also enables precalculation of prompt tokens on the Azure API Management side, minimizing unnecessary requests to the AI service backend if the prompt already exceeds the limit. 
+This policy provides flexibility to assign token-based limits on any counter key, such as subscription key, originating IP address, or an arbitrary key defined through a policy expression. The policy also enables precalculation of prompt tokens on the Azure API Management side, minimizing unnecessary requests to the Foundry Tool backend if the prompt already exceeds the limit. 
 
 The following basic example demonstrates how to set a TPM limit of 500 per subscription key:
 
@@ -102,7 +102,7 @@ More information:
 
 ### Semantic caching
 
-Semantic caching is a technique that improves the performance of LLM APIs by caching the results (completions) of previous prompts and reusing them by comparing the vector proximity of the prompt to prior requests. This technique reduces the number of calls made to the AI service backend, improves response times for end users, and can help reduce costs.
+Semantic caching is a technique that improves the performance of LLM APIs by caching the results (completions) of previous prompts and reusing them by comparing the vector proximity of the prompt to prior requests. This technique reduces the number of calls made to the Foundry Tool backend, improves response times for end users, and can help reduce costs.
 
 In API Management, enable semantic caching by using [Azure Managed Redis](/azure/redis/overview) or another external cache compatible with RediSearch and onboarded to Azure API Management. By using the Embeddings API, the [llm-semantic-cache-store](llm-semantic-cache-store-policy.md) and [llm-semantic-cache-lookup](llm-semantic-cache-lookup-policy.md) policies store and retrieve semantically similar prompt completions from the cache. This approach ensures completions reuse, resulting in reduced token consumption and improved response performance. 
 
@@ -124,13 +124,13 @@ More information:
 * [Deploy an API Management instance in multiple regions](api-management-howto-deploy-multi-region.md)
 
 > [!NOTE]
-> While API Management can scale gateway capacity, you also need to scale and distribute traffic to your AI backends to accommodate increased load (see the [Resiliency](#resiliency) section). For example, to take advantage of geographical distribution of your system in a multiregion configuration, deploy backend AI services in the same regions as your API Management gateways.
+> While API Management can scale gateway capacity, you also need to scale and distribute traffic to your AI backends to accommodate increased load (see the [Resiliency](#resiliency) section). For example, to take advantage of geographical distribution of your system in a multiregion configuration, deploy backend Foundry Tools in the same regions as your API Management gateways.
 
 ## Security and safety
 
 An AI gateway secures and controls access to your AI APIs. By using the AI gateway, you can:
 
-* Use managed identities to authenticate to Azure AI services, so you don't need API keys for authentication
+* Use managed identities to authenticate to Foundry Tools, so you don't need API keys for authentication
 * Configure OAuth authorization for AI apps and agents to access APIs or MCP servers by using API Management's credential manager
 * Apply policies to automatically moderate LLM prompts by using [Azure AI Content Safety](/azure/ai-services/content-safety/overview)
 
@@ -146,7 +146,7 @@ More information:
 
 ## Resiliency
 
-One challenge when building intelligent applications is ensuring that the applications are resilient to backend failures and can handle high loads. By configuring your LLM endpoints with [backends](backends.md) in Azure API Management, you can balance the load across them. You can also define circuit breaker rules to stop forwarding requests to AI service backends if they're not responsive. 
+One challenge when building intelligent applications is ensuring that the applications are resilient to backend failures and can handle high loads. By configuring your LLM endpoints with [backends](backends.md) in Azure API Management, you can balance the load across them. You can also define circuit breaker rules to stop forwarding requests to Foundry Tool backends if they're not responsive. 
 
 ### Load balancer 
 

articles/api-management/openai-compatible-llm-api.md

@@ -15,15 +15,15 @@ ms.custom: template-how-to
 
 [!INCLUDE [api-management-availability-all-tiers](../../includes/api-management-availability-all-tiers.md)]
 
-You can import OpenAI-compatible language model endpoints to your API Management instance as APIs. You can also import language models that aren't compatible with OpenAI as passthrough APIs, which forward requests directly to the backend endpoints. For example, you might want to manage an LLM that you self-host, or that's hosted on an inference provider other than Azure AI services. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
+You can import OpenAI-compatible language model endpoints to your API Management instance as APIs. You can also import language models that aren't compatible with OpenAI as passthrough APIs, which forward requests directly to the backend endpoints. For example, you might want to manage an LLM that you self-host, or that's hosted on an inference provider other than Foundry Tools. Use AI gateway policies and other capabilities in API Management to simplify integration, improve observability, and enhance control over the model endpoints.
 
 Learn more about managing AI APIs in API Management:
 
 * [AI gateway capabilities in Azure API Management](genai-gateway-capabilities.md)
 
 ## Language model API types
 
-API Management supports two types of language model APIs for this scenario. Choose the option suitable for your model deployment. The option determines how clients call the API and how the API Management instance routes requests to the AI service.
+API Management supports two types of language model APIs for this scenario. Choose the option suitable for your model deployment. The option determines how clients call the API and how the API Management instance routes requests to the Foundry Tool.
 
 * **OpenAI-compatible** - Language model endpoints that are compatible with OpenAI's API. Examples include certain models exposed by inference providers such as [Hugging Face Text Generation Inference (TGI)](https://huggingface.co/docs/text-generation-inference/en/index) and [Google Gemini API](openai-compatible-google-gemini-api.md).
 

articles/api-management/sap-api.md

@@ -1,5 +1,5 @@
 ---
-title: Import an SAP API by Using the Azure Portal | Microsoft Docs
+title: Import an SAP API by Using the Azure portal | Microsoft Docs
 titleSuffix:
 description: Learn how to import OData metadata from SAP as an API to Azure API Management, either directly or by converting the metadata to an OpenAPI specification.
 ms.service: azure-api-management