Get pod metrics data. | NVIDIA Run:ai Documentation

curl -G http://localhost:8080/api/v1/workloads/workloadId/pods/podId/metrics \
     -H "Authorization: Bearer <token>" \
     --data-urlencode end=2023-06-07T12:09:18.211Z \
     -d metricType=GPU_UTILIZATION_PER_GPU \
     --data-urlencode start=2023-06-06T12:09:18.211Z

{
  "measurements": [
    {
      "type": "ALLOCATED_GPU",
      "values": [
        {
          "value": "85",
          "timestamp": "2024-12-20T14:30:00Z"
        },
        {
          "value": "92",
          "timestamp": "2024-12-20T14:30:30Z"
        },
        {
          "value": "78",
          "timestamp": "2024-12-20T14:37:00Z"
        }
      ],
      "labels": {
        "gpu": "0"
      }
    }
  ],
  "histogram": [
    {
      "type": "NIM_TIME_TO_FIRST_TOKEN_SECONDS",
      "values": [
        {
          "timestamp": "2024-12-20T14:30:00Z",
          "data": {
            "+Inf": "1024",
            "0.001": "45",
            "0.005": "178",
            "0.01": "312",
            "0.05": "624",
            "0.1": "812",
            "0.5": "980",
            "1.0": "1004",
            "2.0": "1015"
          }
        },
        {
          "timestamp": "2024-12-20T14:30:30Z",
          "data": {
            "+Inf": "960",
            "0.001": "32",
            "0.005": "152",
            "0.01": "288",
            "0.05": "576",
            "0.1": "756",
            "0.5": "908",
            "1.0": "932",
            "2.0": "943"
          }
        }
      ]
    },
    {
      "type": "NIM_TIME_TO_FIRST_TOKEN_SECONDS_PERCENTILES",
      "values": [
        {
          "timestamp": "2024-12-20T14:30:00Z",
          "data": {
            "p50": "0.0734",
            "p90": "0.1892",
            "p99": "0.2847"
          }
        },
        {
          "timestamp": "2024-12-20T14:30:30Z",
          "data": {
            "p50": "0.0823",
            "p90": "0.2134",
            "p99": "0.3156"
          }
        }
      ]
    }
  ]
}

Retrieve pod's metrics data for use in analysis applications.

Authentication

AuthorizationBearer

Bearer authentication

Path parameters

workloadIdstringRequiredformat: "uuid"

The Universally Unique Identifier (UUID) of the workload.

podIdstringRequiredformat: "uuid"

The requested pod id.

Query parameters

metricTypelist of enumsRequired

Specify which metric data to request. Advanced GPU metrics are only supported if the 'Advanced GPU Metrics' feature flag in the settings is enabled.

startdatetimeRequired

Start date of time range to fetch data in ISO 8601 timestamp format.

enddatetimeRequired

End date of time range to fetch data in ISO 8601 timestamp format.

numberOfSamplesintegerOptional0-1000Defaults to 20

The number of samples to take in the specified time range.

Response

Executed successfully.

measurementslist of objects

histogramlist of objects or nullOptional

Errors

400

Bad Request Error

401

Unauthorized Error

403

Forbidden Error

404

Not Found Error

500

Internal Server Error

503

Service Unavailable Error