{
  "opencollection": "1.0.0",
  "info": {
    "name": "Triton Inference Server NVIDIA Triton Inference Server HTTP/REST CUDA Shared Memory Metrics API",
    "version": "2.0"
  },
  "items": [
    {
      "info": {
        "name": "Metrics",
        "type": "folder"
      },
      "items": [
        {
          "info": {
            "name": "Triton Inference Server Get Prometheus metrics",
            "type": "http"
          },
          "http": {
            "method": "GET",
            "url": "http://localhost:8000/metrics"
          },
          "docs": "Retrieve all available metrics in Prometheus text exposition format. Includes server-level metrics (request counts, latencies, GPU utilization, memory usage) and per-model metrics (inference counts, queue times, compute times). Metrics are labeled with model name, version, GPU UUID, and other dimensions.\n\nKey metric families include:\n- `nv_inference_request_success` - Successful inference request count\n- `nv_inference_request_failure` - Failed inference request count\n- `nv_inference_count` - Tot"
        }
      ]
    }
  ],
  "bundled": true
}