Vulgar language

Detects profanity from mild to severe, along with targeted insults and harassment aimed at a specific person. Genuine discussion or education about sensitive language still passes.

What it blocks

• Mild to severe profanity
• Targeted insults and harassment directed at a person

Where this matters

Community platforms, comment sections, and live chat where users post publicly or interact directly, without nuking every conversation.

Performance

• Typical latency well under 200ms on short inputs
• Exact profanity matched instantly by the rules filter
• Context-aware detection keeps genuine discussion unflagged

Technical

• Model ID: vulgar in POST /v1/moderate
• Rules filter runs first, then a task fine-tuned transformer
• 256-token window with overlapping chunking for longer inputs
• Safe or not safe verdict with latency in milliseconds

Example prompts