FAVUR
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, 63 model requests from 5 agents landed at once - 2.1 times the run's typical five-minute spend. The burst bought something: the code-review agent finished its job.

Where this happened.

Source events.

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

  • 75396851-412d-497a-9822-7ba5e519164a
  • 5c686114-99fd-4852-99f7-942528d630d0