Content moderation / PII redaction / trust & safety

compliance

Toxicity classification, PII redaction, and CSAM hash-matching — the guardrail shelf for any agent acting on user-generated content or handling personal data.

AXP admission — verdict pending — no ratified api.qa digest for this listing yet

sources: toxicity classifiers, PII scrubbing, CSAM hash-match
pricing: per call · per 1K tokens