Get replica machine metrics
Dedicated Inference
Get replica machine metrics
Get GPU and system metrics from Prometheus for a specific inference replica.
Mirrors GET /execution//metrics but keyed on an inference
deployment’s replica. Uses replica.node_id as the Prometheus instance label.
GET
Get replica machine metrics
Path Parameters
Query Parameters
ISO 8601 start timestamp (defaults to replica.created_at)
ISO 8601 end timestamp (defaults to replica.last_health_check if terminated, otherwise now)
Query resolution (e.g., '5s', '15s', '1m')
Response
Successful Response
Resource-agnostic machine-level GPU+system metrics response.
Time range for the metrics query.

