OpenAI Moderation
Default first-pass content filter for agent I/O. Pair with Llama Guard (Groq) or NeMo Guardrails when you…
Default first-pass content filter for agent I/O. Pair with Llama Guard (Groq) or NeMo Guardrails when you need open/custom policies. Strengths: Free, fast, zero infra; Text + image multimodal classification; Inline with generation APIs.
Lock-in risk: higher = more lock-in (worse). Overall already inverts this dimension.
Default first-pass content filter for agent I/O. Pair with Llama Guard (Groq) or NeMo Guardrails when you need open/custom policies.
Strengths
- · Free, fast, zero infra
- · Text + image multimodal classification
- · Inline with generation APIs
Weaknesses
- · Fixed OpenAI taxonomy — not your policy engine
- · Cannot self-host or fine-tune categories
- · Audio not classified
Pricing notes
As of 2026-09-14: Free moderation endpoint — omni-moderation-latest for text+images (images ≤20 MB). Also inline moderation on Responses/Chat Completions via moderation.model. Categories include hate, harassment, self-harm, sexual, violence, illicit, etc. Not customizable / not self-hostable.
Sourced pricing
Contract status unit_mismatch · unit_mismatch. Single normalized $/1M: null. Machine list: /api/pricing?provider=openai-moderation
- omni-moderation-latest (moderation endpoint) · usd_per_1k_requests · $0 · unit_mismatch · normalized null
Community signals
Insight claims only — never mutate official scores. Outside reports: 0; seed examples: 0.
No insights yet. Submit a production claim →
All insights for this provider →