curl --request POST \
  --url https://api.iotools.cloud/v1/tool/server-capacity-calculator \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "knownPair": "rw",
  "arrivalRate": "50",
  "responseTime": "200",
  "concurrency": "10",
  "perInstanceCapacity": "20",
  "targetThroughput": "75"
}
'

{
  "tool": "server-capacity-calculator",
  "tool_version": "1.0.2",
  "outputs": {
    "resultTable": [
      {
        "metric": "Arrival Rate (λ)",
        "value": "50 req/s"
      },
      {
        "metric": "Avg Response Time (W)",
        "value": "200 ms"
      },
      {
        "metric": "Concurrency (L)",
        "value": "10 in-flight requests"
      },
      {
        "metric": "Utilization at current load",
        "value": "250%"
      },
      {
        "metric": "Instances needed at current load",
        "value": "3"
      }
    ],
    "scalingTable": [
      {
        "traffic-level": "50% of target",
        "throughput-req-s": "37.5",
        "utilization": "46.875%"
      },
      {
        "traffic-level": "75% of target",
        "throughput-req-s": "56.25",
        "utilization": "70.3125%"
      },
      {
        "traffic-level": "100% of target (baseline)",
        "throughput-req-s": "75",
        "utilization": "93.75%"
      },
      {
        "traffic-level": "125% of target",
        "throughput-req-s": "93.75",
        "utilization": "117.188%"
      },
      {
        "traffic-level": "150% of target",
        "throughput-req-s": "112.5",
        "utilization": "140.625%"
      },
      {
        "traffic-level": "200% of target",
        "throughput-req-s": "150",
        "utilization": "187.5%"
      }
    ],
    "formulas": "Known: Arrival Rate (λ) & Response Time (W)\nSolved: Concurrency (L)\n\nLittle's Law:\n  L = λ × W\n  L = 50 req/s × 0.2 s = 10 in-flight requests\n\nUtilization (current load):\n  Utilization = λ ÷ μ\n  Utilization = 50 ÷ 20 = 2.5 (250%)\n  Instances = ceil(Utilization) = ceil(2.5) = 3\n\nInstances needed for target throughput (75 req/s):\n  Instances = ceil(target ÷ μ) = ceil(75 ÷ 20) = 4\n\nScaling table assumes 4 instance(s) — sized for the target throughput above — and shows how full the fleet gets at other traffic levels."
  },
  "credits_used": 5,
  "credits_remaining": null
}