Get aggregated metrics with time series for any aggregation level

curl -G /v2/metrics \
     -d computeZoneId=550e8400-e29b-41d4-a716-446655440000 \
     -d computeZoneName=training-computezone \
     -d groupBy=nodegroup \
     -d groupId=550e8400-e29b-41d4-a716-446655440000 \
     -d groupName=training-nodegroup \
     --data-urlencode metricNames=dcgm_fi_dev_gpu_util,cpu_used_percent \
     -d nodeGroupName=training-nodegroup \
     -d step=5m \
     -d window=24h

{
  "metrics": [
    {
      "unavailable": {
        "code": "sensorNotPresent",
        "message": "This node does not report the sensors for this metric."
      },
      "warning": {
        "code": "invalidMetricValues",
        "message": "1 data point(s) had invalid values and were omitted."
      },
      "aggregation": "average",
      "displayName": "GPU Utilization",
      "emptyStateMessage": "No error detected",
      "falseLabel": "Down",
      "name": "dcgm_fi_dev_gpu_util",
      "result": [
        {
          "displayLabel": "GPU 0",
          "label": {},
          "values": "[[1705276800, 0.723], [1705277100, 0.741]]"
        }
      ],
      "trueLabel": "Up",
      "unit": "ratio"
    }
  ],
  "step": "5m",
  "timeRange": {
    "end": "2024-01-01T01:00:00Z",
    "start": "2024-01-01T00:00:00Z"
  }
}

Returns historical chart data for customer, node group, compute zone, or node level. The service selects the appropriate query path for each metric and aggregation level. Aggregation functions are determined by metric configuration in base-config.yaml.

Query parameters

groupByenumRequired

The aggregation level to group metrics by

Allowed values:

groupIdstringOptional

Entity ID for node, nodegroup, or computezone queries.

groupNamestringOptional

Legacy generic entity name. Prefer nodeGroupName for nodegroup and computeZoneName for computezone.

nodeGroupNamestringOptional

The node group name for nodegroup level when computeZoneId or computeZoneName is also provided.

computeZoneIdstringOptional

The compute zone ID disambiguator when querying nodegroup by name.

computeZoneNamestringOptional

The compute zone name for computezone level, or disambiguator with nodeGroupName.

metricNameslist of stringsRequired

Comma-separated list of metric names to query (e.g., dcgm_fi_dev_gpu_util,cpu_used_percent,memory_used_percent)

startTimestringOptional

Start time in RFC3339 format (required for absolute mode, e.g., 2024-01-01T00:00:00Z)

endTimestringOptional

End time in RFC3339 format (required for absolute mode, e.g., 2024-01-01T01:00:00Z)

timeModeenumOptional

Time mode for range selection. Defaults to absolute.

Allowed values:

windowstringOptional

Relative duration window (required for relative mode). Uses Go duration syntax — valid units: h, m, s (e.g. 24h, 1h30m, 90m). ‘d’ is not supported; use hours instead (e.g. 168h for 7 days)

stepstringRequired

Query resolution step width in duration format (e.g., 1m, 5m, 1h). Minimum step width is 1 minute.

Response

Metrics with time series for the requested aggregation level

metricslist of objectsOptional

stepstringOptional

Query resolution step width from request

timeRangeobjectOptional

Errors

499

Client Closed Request Error