An object representing an error response from the Eval API.
The reason why the sample generation was finished.
An array of input messages.
The maximum number of tokens allowed for completion.
The model used for generating the sample.
An array of output messages.
The seed used for generating the sample.
The sampling temperature used.
The top_p value used for sampling.
Token usage details for the sample.
A sample containing the input and output of the evaluation run.