AWS Bedrock metrics

Amazon Bedrock is a fully managed, serverless service for building and scaling generative AI applications on foundation models from a range of AI providers. Ensure your cloud platform is configured in SolarWinds Observability SaaS to collect this service's data. See Add an AWS cloud account. CloudWatch metrics must also be enabled for this service in the AWS Console for the metric data to be available.

Each foundation model is monitored as a separate entity, identified by its model ID. A base model uses a standardized ID such as anthropic.claude-v2, while a custom model uses the ARN that AWS generates for it.

Only the foundation models that your knowledge bases and agents use are discovered. AWS does not report the full set of base models that are enabled on an account; therefore, models that you have access to but have not used do not appear.

Many of the collected metrics from AWS Bedrock 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 AWS Bedrock metrics in the Metrics Explorer, type AWS.Bedrock in the search box.

Metric	Units	Description
sw.metrics.healthscore	Percent (%)	Health state. The health state provides real-time insight into the overall health and performance of your monitored entities. The health state is determined based on anomalies detected for the entity, alerts triggered for the entity's metrics, and the status of the entity. The health state is displayed as one of the following four states and colors: Good, Moderate, Bad, or Unknown. You can determine the impact of the alerts, anomalies, and statuses on the health of an entity type by going to Settings > Health, and selecting a specific entity type. You can also customize the impact. To view the health of AWS Bedrock entities in the Metrics Explorer, filter the sw.metrics.healthscore metric by entity_types and select awsbedrock.
AWS.Bedrock.Invocations	Count	The number of successful requests to the Converse, ConverseStream, InvokeModel, and InvokeModelWithResponseStream API operations.
AWS.Bedrock.InvocationLatency	Milliseconds (ms)	The time from when a request is sent to when the last token is received.
AWS.Bedrock.InvocationClientErrors	Count	The number of invocations that result in a client-side error.
AWS.Bedrock.InvocationServerErrors	Count	The number of invocations that result in an AWS server-side error.
AWS.Bedrock.InvocationThrottles	Count	The number of invocations that the system throttled, for example because a quota was exceeded. Throttled requests are not counted as invocations or as errors.
AWS.Bedrock.InputTokenCount	Count	The number of tokens in the input.
AWS.Bedrock.OutputTokenCount	Count	The number of tokens in the output.
AWS.Bedrock.OutputImageCount	Count	The number of images in the output. Applies to image generation models only.