OpenAI Privacy Filter: An Open-Weights PII Detection Model

Melvin Vivas · X post · 2026-04-23 · Open on X

Topics: AI Safety, Security & Guardrails · Level: beginner

Summary

OpenAI released Privacy Filter, an open-weights model for detecting personally identifiable information (PII). It has 1.5B total parameters with 50M active and is available on Hugging Face.

Key points

• Privacy Filter is OpenAI's open-weights model for detecting PII.
• It has 1.5B total parameters but only 50M active (a sparse design).
• It is available on Hugging Face.

Resources mentioned

• OpenAI Privacy Filter · tool · openai.com · free
  Small open-weight OpenAI model for context-aware PII detection and redaction.
  Also in: OpenAI Privacy Filter for Local PII Detection and Redaction (Melvin Vivas on X · notes)
• Hugging Face · website · x.com · free · recommended by both Bashiri Smith & Melvin Vivas
  Platform for hosting and finding ML models, datasets and papers. The quoted post says LocateAnything was trending there.
  Also in: Using an ML agent to train an open-source TTS model on your voice (Melvin Vivas on X · notes), Deploy Open-Source Models with Hugging Face Inference Endpoints (Melvin Vivas on X · notes), Deploying Qwen3.8 27B on Hugging Face Inference Endpoints (Melvin Vivas on X · notes), Using Hugging Face credits: Jobs, Inference Endpoints and Open Models (Melvin Vivas on X · notes) and 38 more

Try this

• Try OpenAI Privacy Filter from Hugging Face for detecting PII.