Get Trace Metrics | NVIDIA NeMo Helix

{
  "bucket": "total",
  "timezone": "string",
  "data": [
    {
      "run_count": 1,
      "failed_run_count": 1,
      "input_tokens": {
        "sum": 1,
        "mean": 1.1,
        "p90": 1.1,
        "p99": 1.1
      },
      "output_tokens": {
        "sum": 1,
        "mean": 1.1,
        "p90": 1.1,
        "p99": 1.1
      },
      "cached_tokens": {
        "sum": 1,
        "mean": 1.1,
        "p90": 1.1,
        "p99": 1.1
      },
      "total_tokens": {
        "sum": 1,
        "mean": 1.1,
        "p90": 1.1,
        "p99": 1.1
      },
      "cost_usd": {
        "sum": 1.1,
        "mean": 1.1,
        "p90": 1.1,
        "p99": 1.1
      },
      "latency_ms": {
        "mean": 1.1,
        "p50": 1.1,
        "p90": 1.1,
        "p95": 1.1,
        "p99": 1.1
      },
      "bucket_start": "2024-01-15T09:30:00Z"
    }
  ]
}

Path parameters

workspacestringRequired

Query parameters

bucketenumOptionalDefaults to day

Time bucket granularity. total collapses the filtered range into a single row.

Allowed values:

timezonestringOptionalDefaults to UTC

IANA timezone the buckets are aligned to, e.g. America/Los_Angeles.

filterobjectOptional

Filter the traces the metrics are computed over. Accepts the same fields as the traces list, so agent_name scopes the rollup to one agent. Without a started_at lower bound the rollup covers the last 7 days.

Response

Successful Response

bucketenum

Allowed values:

timezonestring

datalist of objects

Errors

400

Bad Request Error

422

Unprocessable Entity Error

503

Service Unavailable Error