OpenResponsesEvaluatorModelConfig
The configuration for using models served through the OpenResponses API in evaluator assessments, including model selection and inference parameters.
Contents
- modelId
-
The identifier of the model to use for evaluation.
Type: String
Required: Yes
- maxOutputTokens
-
The maximum number of tokens to generate in the model response, including visible output and reasoning tokens.
Type: Integer
Valid Range: Minimum value of 1.
Required: No
- reasoning
-
The reasoning configuration for reasoning models. Non-reasoning models ignore this configuration.
Type: ReasoningConfiguration object
Required: No
- temperature
-
The temperature value that controls randomness in the model's responses. Lower values produce more deterministic outputs.
Type: Float
Valid Range: Minimum value of 0. Maximum value of 2.
Required: No
- topP
-
The top-p sampling parameter that controls the diversity of the model's responses by limiting the cumulative probability of token choices.
Type: Float
Valid Range: Minimum value of 0. Maximum value of 1.
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following:
