OpenAI Service metrics

Azure OpenAI is a feature that empowers users with advanced AI capabilities through OpenAI powerful models, enabling seamless integration of natural language processing, machine learning, and AI-driven insights into applications across various environments, whether in the cloud, on-premises, or hybrid setups. Use the Azure Resource Manager to gather metrics for this resource, then ensure your cloud platform is configured in SolarWinds Observability SaaS to collect this resource type's data. See Add an Azure cloud account.

Depending on the subscription pricing tier of your Azure account or its resources, additional metrics may be available for this entity. To collect additional Azure metrics, select the premium pricing tier when configuring your Azure namespaces.

Many of the collected metrics from OpenAI Service entities are displayed as widgets in SolarWinds Observability explorers; additional metrics may be collected and available in the Metrics Explorer. You can also create an alert for when an entity's metric value moves out of a specific range. See Entities in SolarWinds Observability SaaS for information about entity types in SolarWinds Observability SaaS.

The following table lists some of the metrics collected for these entities. To see the OpenAI Service metrics in the Metrics Explorer, type azure.openai in the search box.

Metric	Units	Description
sw.metrics.healthscore	Percent (%)	Health score. A health score provides real-time insight into the overall health and performance of your monitored entities. The health score is calculated based on anomalies detected for the entity, alerts triggered for the entity's metrics, and the status of the entity. The health score is displayed as a single numerical value that ranges from a Good (70-100) to Moderate (40-69) to Bad (0-39) distinction. To view the health score for OpenAI Service entities in the Metrics Explorer, filter the sw.metrics.healthscore metric by entity_types and select azureopenai.
azure.openai.AzureOpenAIProvisionedManagedUtilizationV2	Percent (%)	The utilization of provisioned managed throughput in Azure OpenAI. This metric helps track the efficiency of allocated processing capacity for AI workloads.
azure.openai.AzureOpenAITimeToResponse	milliseconds (ms)	The time taken for Azure OpenAI to generate a response after receiving a request. This metric is useful for monitoring latency and performance.
azure.openai.TotalEvents	Count	The total number of events processed by Azure OpenAI, including requests, completions, and other interactions.
azure.openai.AzureOpenAIRequests	Count	The total number of requests sent to Azure OpenAI, helping monitor usage and workload demand.
azure.openai.ActiveTokens	Count	The number of active tokens being processed in Azure OpenAI, which can indicate the complexity and scale of ongoing operations.
azure.openai.ProcessedPromptTokens	Count	The number of prompt tokens processed by Azure OpenAI, helping assess input complexity and resource consumption.
azure.openai.TokenTransaction	Count	Represents the number of token transactions processed by Azure OpenAI, tracking usage and billing-related metrics.
azure.openai.GeneratedTokens	Count	The total number of tokens generated by Azure OpenAI models in response to user queries.
azure.openai.FineTunedTrainingHours	Count	The number of hours spent fine-tuning models in Azure OpenAI, helping monitor resource consumption and optimization.
azure.openai.ClientErrors	Count	Errors caused by incorrect or invalid requests from users, such as authentication failures or malformed API calls.
azure.openai.ServerErrors	Count	Errors occurring on the server side, such as internal failures or service outages.
azure.openai.AvailabilityRate	Percent (%)	The percentage of time Azure OpenAI services are available and operational, helping assess reliability and uptime.