The page has been translated by Gen AI.

ServiceWatch Metrics

AIOS sends metrics to ServiceWatch. The metrics provided by default monitoring are data collected at 5‑minute intervals.

Reference
Refer to the ServiceWatch guide for how to view metrics in ServiceWatch.

Basic Metrics

The following are the basic metrics for the AIOS namespace.

The indicators whose names are shown in bold below are the indicators selected as major indicators among the basic indicators provided by AIOS. Key metrics are used to build service dashboards that are automatically created for each service in ServiceWatch.

Each metric indicates through the user guide which statistical value is meaningful when viewing that metric, and among the meaningful statistics, the statistical values shown in bold text are the primary statistics. In the service dashboard, primary metrics can be viewed using the primary statistical values.

Performance itemsDetailed descriptionunitmeaningful statistics
Model Request SuccessNumber of successful model requestsCount
  • Total
Model Request Server ErrorNumber of model request failures (server error)Count
  • Total
Model Request Client ErrorModel request failure count (client error)Count
  • Total
Model Request ThrottledThe number of model requests is limitedCount
  • Total
Model Total TokensModel token usage (total)Count
  • Total
Model Input TokensModel token usage (input)Count
  • Total
Model Output TokensModel token usage (output)Count
  • Total
Model Cached TokensNumber of input tokens reused through cacheCount
  • Total
Table. AIOS basic indicators
Overview
How-to Guides