OptionalresponseOptionalcategories?: string[]Optionalsafe?: booleanWhether the conversation is safe or not.
OptionalusageUsage statistics for the inference request
Optionalcompletion_tokens?: numberTotal number of tokens in output
Optionalprompt_tokens?: numberTotal number of tokens in input
Optionaltotal_tokens?: numberTotal number of input and output tokens
A list of what hazard categories predicted for the conversation, if the conversation is deemed unsafe.