model: str

The moderation model to use for moderated completions, e.g. ‘omni-moderation-latest’.

policy: Optional[ModerationPolicy]

The policy to apply to moderated response input and output.

input: Optional[ModerationPolicyInput]

The moderation policy for the response input.

mode: Literal["score", "block"]
One of the following:
"score"
"block"
output: Optional[ModerationPolicyOutput]

The moderation policy for the response output.

mode: Literal["score", "block"]
One of the following:
"score"
"block"