edits

Author: gitName

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

@@ -104,14 +104,14 @@ In API Management, enable semantic caching by using Azure Redis Enterprise or an
 > [!TIP]
 > To enable semantic caching for LLM APIs available through the Azure AI Model Inference API, API Management provides the equivalent [llm-semantic-cache-store-policy](llm-semantic-cache-store-policy.md) and [llm-semantic-cache-lookup-policy](llm-semantic-cache-lookup-policy.md) policies.
 
-## Azure Monitor logging
+## Logging token usage, prompts, and completions
 
-Enable a [diagnostic setting](monitor-api-management.md#enable-diagnostic-setting-for-azure-monitor-logs) in your API Management instance to send logs to Azure Monitor for requests processed by the gateway for large language model REST APIs. For each request, data is logged including token usage (prompt tokens, completion tokens, and total tokens), name of the model used, and optionally the request message and response message. Large requests and responses are split into multiple log entries that are sequentially numbered for later reconstruction if needed.
+Enable a [diagnostic setting](monitor-api-management.md#enable-diagnostic-setting-for-azure-monitor-logs) in your API Management instance to log requests processed by the gateway for large language model REST APIs. For each request, data is sent to Azure Monitor including token usage (prompt tokens, completion tokens, and total tokens), name of the model used, and optionally the request and response messages (prompt and completion). Large requests and responses are split into multiple log entries that are sequentially numbered for later reconstruction if needed.
 
 The API Management administrator can use LLM gateway logs along with API Management gateway logs for scenarios such as the following:
 
 * **Calculate usage for billing** - Calculate usage metrics for billing based on the number of tokens consumed by each application or API consumer (for example, segmented by subscription ID or IP address).
-* **Inspect messages** - Inspect and analyze prompts and completions for debugging or auditing.
+* **Inspect messages** - To help with debugging or auditing, inspect and analyze prompts and completions.
 
 Learn more about [monitoring API Management with Azure Monitor](monitor-api-management.md).
 

articles/api-management/monitor-api-management.md

@@ -3,7 +3,7 @@ title: Monitor Azure API Management
 description: Learn how to monitor Azure API Management using Azure Monitor, including data collection, analysis, and alerting.
 ms.date: 01/06/2025
 ms.custom: horz-monitor
-ms.topic: concept-article
+ms.topic: how-to
 author: dlepow
 ms.author: danlep
 ms.service: azure-api-management
@@ -197,4 +197,5 @@ To see how to set up an alert rule in Azure API Management, see [Set up an alert
 ## Related content
 
 - [API Management monitoring data reference](monitor-api-management-reference.md)
+- [Tutorial: Monitor published APIs](api-management-howto-use-azure-monitor.md)
 - [Monitoring Azure resources with Azure Monitor](/azure/azure-monitor/essentials/monitor-azure-resource)

includes/api-management-log-entry-size-limit.md

@@ -7,6 +7,6 @@ ms.author: danlep
 ---
 
 > [!IMPORTANT]
-> API Management enforces a 32 KB limit for the size of log entries sent to Azure Monitor. The behavior when the logged data exceeds the limit depends on the log category and the data attributes that are logged:
-> * **API Management Gateway logs** - Logged request or response payloads in a log entry, if collected, can be up to 8,192 bytes each. If the combined size of the logged attributes exceeds 32 KB, API Management trims the entry by removing all body and trace content. 
-> * **LLM Gateway logs** - Request or response messages, if collected, are logged up to 32 KB; messages larger than 32 KB are split and logged in 32 KB chunks including sequence numbers for later reconstruction. Request messages and response messages can't exceed 2 MB each.
+> API Management enforces a 32 KB limit for the size of log entries sent to Azure Monitor. The behavior when a log entry exceeds the limit depends on the log category and the data attributes that are logged:
+> * **API Management Gateway logs** - Logged request or response payloads in a log entry, if collected, can be up to 8,192 bytes each. If the combined size of the attributes in an entry exceeds 32 KB, API Management trims the entry by removing all body and trace content. 
+> * **LLM Gateway logs** - LLM request or response messages up to 32 KB in size, if collected, are sent in a single entry. Messages larger than 32 KB are split and logged in 32 KB chunks with sequence numbers for later reconstruction. Request messages and response messages can't exceed 2 MB each.