dots.v2.genAi.custom_evaluation_metrics.post()
Generated on 18 Nov 2026
from DoTs version
v1.25.0
Usage
client.v2.genAi.custom_evaluation_metrics.post(body: ApiCreateCustomEvaluationMetricInputPublic, requestConfiguration?: RequestConfiguration<object>): Promise<undefined | ApiCreateCustomEvaluationMetricOutput>Description
To create a custom LLM-as-judge metric for model evaluation, send a POST request to /v2/gen-ai/custom_evaluation_metrics.
Parameters
configobject optionalConfiguration for a custom model-evaluation metric scored by an LLM judge.
Prompt and model response are always included in the judge context.Show child properties
createdAtstring optionalExample:
2023-01-01T00:00:00ZdeletedAtstring optionalExample:
2023-01-01T00:00:00ZWhen set, the custom metric is soft-deleted and must not appear in pickers.
requiresGroundTruthboolean optionalExample:
trueWhen true, each row must provide ground truth and it is included in the judge context.
When false, ground truth is not required and is not sent to the judge.scoringPromptstring optionalExample:
example stringInstructions for the judge model (multi-line).
turnTypestring optionalWhether the metric is for single-turn or multi-turn evaluations.
updatedAtstring optionalExample:
2023-01-01T00:00:00Z
descriptionstring optionalExample:
"Scores adherence to our support macros"metricNamestring optionalExample:
"My domain tone metric"
Request Sample
Response Example
More Information
See /v2/gen-ai/custom_evaluation_metrics in the API reference for additional detail on responses, headers, parameters, and more.