OptionalchangeAdditional information about the throughput change request
OptionalchangeThe state of the most recent throughput change request
OptionalcurrentThe current concurrency (total CPU) allocated to the endpoint
OptionalcurrentThe current utilization of concurrency as a percentage (0-100)
OptionalcurrentThe current number of replicas allocated to the endpoint
OptionalmaximumThe maximum concurrency allowed for this endpoint
OptionalminimalThe minimum concurrency allowed for this endpoint
OptionalrequestedThe requested concurrency (total CPU) for the endpoint
OptionalrequestedThe requested number of replicas for the endpoint
Throughput information for an AI Search endpoint, including requested and current concurrency settings.