OpenAI · Harm classifier · Last verified 2026-10-15

OpenAI Moderation (omni-moderation)

Unverified

Harm classifier returning per-category scores. Dated snapshot.

What it does

  • Harm classifier returning per-category scores. Dated snapshot.

Pricing

  • Previously recorded as free (not re-checked). [NOT re-verified on 2026-10-15 — carried from prior research; check before relying on it]

Limits

  • Not recorded. [NOT re-verified on 2026-10-15 — carried from prior research; check before relying on it]

Status

  • Previously recorded as generally available. [NOT re-verified on 2026-10-15 — carried from prior research; check before relying on it]

Safety & fit notes

  • Content-safety gate only; not a general decision model.
  • Same pattern applies: deterministic rules own hard constraints; the model is advisory; fail closed on errors.

Sources