{
  "_note": "Copy to cost-inputs.json and replace every value. Nothing here is a real price, a real power figure or a real speed: the zeros are there so that a file you have not filled in fails loudly instead of producing a confident answer. Use the price you would actually pay in your own currency including tax, the working life you would actually plan for, the fraction of that life the machine is really serving requests, your own electricity tariff, and a throughput figure you measured yourself on the workload named below.",
  "workload_definition": "REPLACE: the one workload every machine in this file is being priced for. For example: single user, one request at a time, 2048-token prompt, 256-token answer, on the largest model that machine can serve.",
  "machines": [
    {
      "name": "REPLACE: what this machine or cluster is, with chip and memory",
      "currency": "REPLACE: the currency you typed the price in",
      "workload": "REPLACE: same as workload_definition, restated for this machine",
      "purchase_price": 0,
      "lifetime_years": 0,
      "busy_fraction": 0,
      "average_watts": 0,
      "electricity_price_per_kwh": 0,
      "output_tokens_per_second": 0,
      "model_served": "REPLACE: the model and quantisation this throughput was measured with",
      "measured_on": "REPLACE: the date you measured it"
    },
    {
      "name": "REPLACE: the other side of the comparison",
      "currency": "REPLACE: the currency you typed the price in",
      "workload": "REPLACE: the same workload, or the page will be comparing two different questions",
      "purchase_price": 0,
      "lifetime_years": 0,
      "busy_fraction": 0,
      "average_watts": 0,
      "electricity_price_per_kwh": 0,
      "output_tokens_per_second": 0,
      "model_served": "REPLACE: the model and quantisation this throughput was measured with",
      "measured_on": "REPLACE: the date you measured it"
    }
  ]
}