Measure a baseline before you optimise
Record input, output, and cached tokens plus tool calls and retries for real work, and keep context-window occupancy distinct from billed usage.
Step 1 of 4
Four meters that are not the same number
Track four different things: context size in one request, usage charged across requests, rate limits on throughput, and spend controls on cost. Cached input still takes context space. Repeated requests can reuse that space while adding more billed usage.
Do not assume a dashboard budget stops traffic. A spend alert only notifies; an enforced limit can reject requests. Availability and enforcement delays depend on the provider. OpenAI documents both controls and warns that a hard limit can slightly overshoot. Check the actual setting, keep a small exercise allowance, and stop manually if usage is unclear.
The course is free, but optional provider calls may incur charges. Use existing redacted logs or the simulated fixtures below without opening an API account. Label simulated work honestly; it proves your analysis, not personal savings.