Question

A developer is building a billing dashboard for an internal tool that uses the Messages API (non-streaming). After each request completes, they need to record exactly how many input and output tokens were consumed by that specific call, without having to re-estimate the text themselves. Where should they look to get this accurate per-request count?

Accepted Answer

The `usage` object in the API response, which reports `input_tokens` and `output_tokens` for the call

Answer

The `max_tokens` value they set in the request, since it equals the tokens actually generated

Answer

The `stop_reason` field, which contains the total token count for the response

Answer

A separate call to a word-count endpoint after every request to approximate token totals