Authorizations
Body
application/json
Request model for a trace based evaluation of LLM responses against specified criteria.
Criteria used for evaluation. Begins with one of the following: Reward, Penalize, Passes if, Fails if
A Multi Agent Trace object representing the full trace of agent interactions.
The model core for reward evaluation. Defaults to align-20250503 if not specified.
Available options:
align-20250529, align-lightning-20250731 Whether to evaluate only the latest response or all responses.