choice), a hand-off decision (noul) and a severity (score):
type:
Acting on the answers
How it runs
- One call, one model job. All questions are answered together; latency is close to a single question.
- Independent answers. Each question is scored on its own, so the answer to one question does not depend on which other questions are in the request.
- Billing. Three questions are three decisions, whatever their types.
usage.input_tokenssums the real token counts of the three questions. - Limits. Up to 16 questions per request, any mix of types.