Fittings Profanity Filter

Choose this endpoint when you need both detection (with offsets) and redaction in a single call, especially for real-time content moderation pipelines. It is well-suited for agents that need to flag the exact location of each profanity match for downstream highlighting or logging, while also producing a publish-ready sanitized version of the text. Prefer it over regex-based local filters when you need a maintained, up-to-date profanity dictionary without managing it yourself.

• Text exceeds 20000 UTF-8 bytes — request rejected
• Invalid or multi-character mask value — validation error
• Empty text input — may return empty match list
• Payment failure via x402 protocol — 402 response before processing
• Network timeout on large text near the byte limit