v1

latestOpenAPI 3.0.02026-07-1346146138.4 KB
evaluators

Execute toxicity-detector evaluator

Detect toxic or harmful language

Request Body:

  • input.text (string, required): The text to scan for toxic content
  • config.threshold (float, optional): Detection threshold (default: 0.5)
post/v2/evaluators/toxicity-detector/execute

Request body

Example request

{
  "config": {
    "threshold": 0.5
  },
  "input": {
    "text": "Thank you for your help with this project."
  }
}

Response

OK

is_safeboolean