Control cost and usage

Go beyond the single cumulative budget from Add guardrails and a budget: cap spend per pipeline stage, get notified before a breach becomes a bill shock, and avoid provider cost altogether on repeated prompts. Field-level reference for every block here is in Cost and usage limits →.

GuideWhat you will achieve
Cap spend per pipeline stageSet a separate monthly budget or token cap on the LLM call, Judge, and Jury stages, so one stage’s spend cannot exhaust a shared cumulative limit.
Alert on budget breaches and cost spikesRoute a cost, token, error-rate, or cost-spike alert to Slack, email, or a webhook, so a person is notified without the request being blocked.
Cache repeated responses to cut cost and latencyServe an identical or near-duplicate request from an in-memory cache instead of calling the provider again.