The run's priciest five minutes - 11.2 times a typical window. Every model call is metered, so a run's spend can be read window by window against its own baseline. For five minutes, 27 model requests from 2 agents landed at once - 11.2 times the run's typical five-minute spend. The burst bought something: the scout agent finished its job.

Where this happened.

Source events.

Detected mechanically by the cost_spike detector from 2 telemetry event(s):

  • 2b0ddf89-3f1b-4103-9f0c-54b5f36df878
  • 1460e85f-b730-41d9-be66-e895b7d48d0c