moderation

Checks text for violations of usage policies across categories like hate, harassment, violence, and self-harm.

Syntax

openai-api

client.moderations.create({ input })

Example

openai-api

const moderation = await client.moderations.create({
  input: "User-submitted text here"
});

if (moderation.results[0].flagged) {
  const cats = moderation.results[0].categories;
  console.log("Flagged categories:", cats);
}