Skip to main content
Get endpoint-level summary metrics plus a time series over a lookback window.

​
Run

curl -s "https://api.wafer.ai/v1/endpoints/metrics?endpoint=<ENDPOINT_HOST>&range_minutes=<RANGE_MINUTES>" \
  -H "Authorization: Bearer <API_KEY>"

​
Parameters

  • endpoint (required): <ENDPOINT_HOST>
  • range_minutes (optional): 5, 15, 30, 60, 360, 1440
  • default range_minutes: 60

​
Response Shape

{
  "endpoint": "example-endpoint.wafer.ai",
  "range_minutes": 60,
  "queried_at": "2026-05-01T15:55:19+00:00",
  "summary": {
    "total_requests": 1200,
    "rps": 0.33,
    "ttft_p50_ms": 410.0,
    "ttft_p90_ms": 1250.0,
    "ttft_p99_ms": 3200.0,
    "tps_p50": 92.0,
    "tps_p90": 155.0,
    "latency_p50_ms": 2100.0,
    "latency_p90_ms": 6400.0,
    "latency_p99_ms": 12000.0,
    "cache_hit_pct": 72.5,
    "total_input_tokens": 4800000,
    "total_output_tokens": 420000,
    "total_cache_read_tokens": 3480000,
    "count_2xx": 1184,
    "count_4xx": 16,
    "count_5xx": 0,
    "error_rate_pct": 1.3,
    "concurrent_requests": 12,
    "active_accounts": 1,
    "engine_running_requests": 2.0,
    "engine_queue_depth": 0.0,
    "engine_kv_cache_hit_rate_pct": 68.0,
    "engine_kv_cache_usage_pct": 42.0,
    "engine_preemptions_in_range": 0.0
  },
  "backends": [
    {
      "backend_id": "backend-a",
      "active_requests": null,
      "engine_running_requests": 2.0,
      "engine_queue_depth": 1.0,
      "is_healthy": true
    }
  ],
  "timeseries": [
    {
      "time": "2026-05-01T14:55:00Z",
      "requests": 120,
      "tps_p50": 92.0,
      "ttft_p50_ms": 410.0,
      "latency_p50_ms": 2100.0,
      "error_count": 1
    }
  ]
}

​
Key Fields

  • rps: average requests per second across the full window
  • ttft_p50_ms, ttft_p90_ms, ttft_p99_ms: streaming TTFT percentiles
  • tps_p50, tps_p90: output tokens-per-second percentiles
  • latency_p50_ms, latency_p90_ms, latency_p99_ms: end-to-end latency percentiles
  • cache_hit_pct: cache-read prompt tokens divided by total input tokens
  • count_2xx, count_4xx, count_5xx: request count by status class
  • error_rate_pct: 4xx + 5xx divided by total requests
  • concurrent_requests: recent activity count, not an exact inflight gauge
  • active_accounts: distinct API keys active in the last 2 minutes
  • engine_running_requests: sum of in-flight requests across all backend engines
  • engine_queue_depth: sum of queued requests across all backend engines
  • engine_kv_cache_hit_rate_pct: average KV cache hit rate across backends (percentage)
  • engine_kv_cache_usage_pct: average KV cache utilization across backends (percentage)
  • engine_preemptions_in_range: total engine preemptions during the lookback window
  • backends[*].active_requests: live wafer-edge backend inflight gauge when emitted by the endpoint
  • backends[*].engine_running_requests: live engine running request gauge for that backend/node
  • backends[*].engine_queue_depth: live engine queue depth gauge for that backend/node
  • timeseries[*]: per-bucket requests, tps_p50, ttft_p50_ms, latency_p50_ms, error_count

​
Errors

  • 401: missing or invalid API key
  • 403: API key does not have access to the requested endpoint
  • 422: invalid range_minutes or invalid query shape
  • 502: upstream metrics query failed

​
Notes

  • Metrics are endpoint-scoped. You must pass an endpoint your key can access.
  • For per-request debugging, use Request Inspection.