The run's priciest five minutes - 2.1 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, 39 model requests from 6 agents landed at once - 2.1 times the run's typical five-minute spend. The burst bought something: the checkup agent finished its job.

Where this happened.

Source events.

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

  • 6b54ce20-1443-4332-9bef-395e0b65d088
  • 54681e50-30af-4042-bbf5-ef806b643aba