The run's priciest five minutes - 3.4 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, 78 model requests from 6 agents landed at once - 3.4 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):

  • 1954d0a4-7d5e-46ea-906a-1f1cb07c5c94
  • de615158-59e3-48a0-b26c-d9f208d818a1