{
  "scope": "Solver inference only. Reflection publishes no price for Beam (its public API beta is free to start), so no run is priced: cost is unavailable, not zero. Tokens and minutes are reported instead. Judging is excluded.",
  "pricing": null,
  "groups": [
    {
      "model": "beam",
      "effort": "low",
      "n": 23,
      "usd": null,
      "raw_tokens": {
        "n": 23,
        "mean": 86611.52173913043,
        "se": 5429.486076491994
      },
      "raw_tokens_total": 1992065,
      "output_tokens": {
        "n": 23,
        "mean": 2326.3478260869565,
        "se": 188.67607820008095
      },
      "cached_input_share": {
        "n": 23,
        "mean": 0.8166497622547785,
        "se": 0.010905792877429862
      },
      "model_calls": {
        "n": 23,
        "mean": 12.521739130434783,
        "se": 0.5653693927569556
      },
      "failed_model_requests": 0,
      "minutes": {
        "n": 23,
        "mean": 0.3777913043478261,
        "se": 0.02133749094526402
      }
    },
    {
      "model": "beam",
      "effort": "medium",
      "n": 23,
      "usd": null,
      "raw_tokens": {
        "n": 23,
        "mean": 436557.04347826086,
        "se": 56012.36997717904
      },
      "raw_tokens_total": 10040812,
      "output_tokens": {
        "n": 23,
        "mean": 8520.565217391304,
        "se": 675.8669087653133
      },
      "cached_input_share": {
        "n": 23,
        "mean": 0.9106521029417463,
        "se": 0.004624223767025414
      },
      "model_calls": {
        "n": 23,
        "mean": 32.91304347826087,
        "se": 2.657611221577079
      },
      "failed_model_requests": 0,
      "minutes": {
        "n": 23,
        "mean": 1.9331855072463768,
        "se": 0.46051450499265995
      }
    },
    {
      "model": "beam",
      "effort": "high",
      "n": 23,
      "usd": null,
      "raw_tokens": {
        "n": 23,
        "mean": 3394646.1739130435,
        "se": 281863.6906282533
      },
      "raw_tokens_total": 78076862,
      "output_tokens": {
        "n": 23,
        "mean": 42268.260869565216,
        "se": 2489.7328961436583
      },
      "cached_input_share": {
        "n": 23,
        "mean": 0.9526260259889935,
        "se": 0.003645928300322017
      },
      "model_calls": {
        "n": 23,
        "mean": 93.69565217391305,
        "se": 4.569375106517957
      },
      "failed_model_requests": 0,
      "minutes": {
        "n": 23,
        "mean": 9.201744202898551,
        "se": 1.3814292912022599
      }
    },
    {
      "model": "beam",
      "effort": "extra-high",
      "n": 23,
      "usd": null,
      "raw_tokens": {
        "n": 23,
        "mean": 12417111.304347826,
        "se": 2203962.3470025402
      },
      "raw_tokens_total": 285593560,
      "output_tokens": {
        "n": 23,
        "mean": 86908.91304347826,
        "se": 8160.158128581258
      },
      "cached_input_share": {
        "n": 23,
        "mean": 0.9728170727127985,
        "se": 0.002470933611372363
      },
      "model_calls": {
        "n": 23,
        "mean": 165.08695652173913,
        "se": 15.791241010825255
      },
      "failed_model_requests": 1,
      "minutes": {
        "n": 23,
        "mean": 18.75290507246377,
        "se": 2.7415818250284136
      }
    },
    {
      "model": "beam",
      "effort": "max",
      "n": 23,
      "usd": null,
      "raw_tokens": {
        "n": 23,
        "mean": 17285785.95652174,
        "se": 3471496.7898260597
      },
      "raw_tokens_total": 397573077,
      "output_tokens": {
        "n": 23,
        "mean": 115760.69565217392,
        "se": 15988.85736343532
      },
      "cached_input_share": {
        "n": 23,
        "mean": 0.969021101887774,
        "se": 0.002272950014512173
      },
      "model_calls": {
        "n": 23,
        "mean": 199.95652173913044,
        "se": 25.59354524764707
      },
      "failed_model_requests": 5,
      "minutes": {
        "n": 23,
        "mean": 22.445145652173913,
        "se": 2.759103812073485
      }
    }
  ],
  "totals": {
    "beam": {
      "runs": 115,
      "raw_tokens": 773276376,
      "model_calls": 11596,
      "failed_model_requests": 6,
      "solver_hours": 20.205795833333333,
      "usd": null
    }
  },
  "limitations": [
    "No list price exists for Beam, so the board shows Beam on its tokens and minutes views only.",
    "Tokens are summed from Mirror's per-call usage records; cached input is a subset of input, and Mirror reports no separate reasoning count.",
    "Six model requests in five runs failed (three \"temporarily unavailable\", three HTTP 520) and Mirror carried on; they report no usage.",
    "Tokens and minutes cover all 23 runs at every level, judged or not."
  ]
}