Report tokens and cost

AMC reads GET /runs/{id}/tokens and GET /runs/{id}/status on every poll, so report running totals while the run is live: department budget spend counts in-flight runs.

{
  "orchestratorRunId": "run_5f2c0e8a41b94c55",
  "agentTokens": 4810,
  "hostTokens": 0,
  "totalTokens": 4810,
  "inputTokens": 4200,
  "outputTokens": 610,
  "costUsd": 0
}

Per-step fields

How AMC prices a run

1. 1If /tokens reports costUsd greater than zero, that is the run's cost.
2. 2Otherwise AMC prices each step: by modelUsage when present (each model at its own rate, summed), else by model and the step's tokens. A missing or unknown model uses AMC's default rate.
3. 3If that comes to zero (no split reported), ROI estimates cost from totalTokens at a flat per-token rate.

uncached = inputTokens - cachedInputTokens
cost     = uncached          / 1,000,000 x input rate
         + cachedInputTokens / 1,000,000 x cached input rate
         + outputTokens      / 1,000,000 x output rate

Report costUsd when your provider gives you an exact figure (for example, the Claude Agent SDK's total cost). It wins over any recompute. Keep reporting tokens and model anyway: they drive the per-step and per-model breakdown people see.

Failed and cancelled runs

Spend before a failure is real. Keep the tokens on the step that failed and in /tokens, or the failed run prices at zero. On cancel, AMC reads /tokens one last time, so report what the run spent up to the cancel.

{
  "stepId": "research",
  "name": "Research",
  "status": "completed",
  "tokenCount": 51200,
  "inputTokens": 48000,
  "outputTokens": 3200,
  "cachedInputTokens": 30000,
  "model": "<orchestrator-model-id>",
  "modelUsage": [
    { "model": "<orchestrator-model-id>", "inputTokens": 40000, "outputTokens": 2500, "cachedInputTokens": 28000 },
    { "model": "<subagent-model-id>", "inputTokens": 8000, "outputTokens": 700, "cachedInputTokens": 2000 }
  ]
}