usage block

The part of a model reply that reports how many tokens the call read and wrote, split by type, which is what you are billed for.

In more detail

Anthropic reports uncached input, cache writes and cache reads separately, with output (thinking included) on its own; OpenAI counts cached tokens inside its input total. Log usage with the request id on every call, and price each count at its own rate.

Related terms

Taught in

References

Certification courses