# OpenAI Privacy Filter for detecting and masking PII in text

**URL:** <https://community.openai.com/t/openai-privacy-filter-for-detecting-and-masking-pii-in-text/1379537>\
**Category:** Open Models\
**Tags:** announcement, pii\
**Created:** [April 22, 2026, 5:39pm UTC](https://community.openai.com/t/openai-privacy-filter-for-detecting-and-masking-pii-in-text/1379537 "2026-04-22T17:39:45Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![VeitB](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/veitb/32/712987_2.png) [@VeitB](https://community.openai.com/u/VeitB)\
**Post date:** [April 22, 2026, 5:39pm UTC](https://community.openai.com/t/openai-privacy-filter-for-detecting-and-masking-pii-in-text/1379537/1 "2026-04-22T17:39:45Z")

</div>

OpenAI has published Privacy Filter, a small model for detecting and masking PII in text. It can run locally, supports a 128k context window, and comes with tools for redaction, evaluation, and fine-tuning. Looks especially useful for teams that need fast, on-prem privacy filtering with control over precision and recall.

Highlights:

- Permissive Apache 2.0 license: ideal for experimentation, customization, and commercial deployment.
- Small size: Runs in a web browser or on a laptop – 1.5B parameters total and 50M active parameters.
- Fine-tunable: Adapt the model to specific data distributions through easy and data efficient finetuning.
- Long-context: 128,000-token context window enables processing long text with high throughput and no chunking.
- Runtime control: configure precision/recall tradeoffs and detected span lengths through preset operating points.

> **[GitHub - openai/privacy-filter: OpenAI Privacy Filter](https://github.com/openai/privacy-filter)**
>
> OpenAI Privacy Filter

---

<div class="post-metadata">

**Author:** ![EricGT](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ericgt/32/20571_2.png) [@EricGT](https://community.openai.com/u/EricGT)\
**Post date:** [April 22, 2026, 6:54pm UTC](https://community.openai.com/t/openai-privacy-filter-for-detecting-and-masking-pii-in-text/1379537/2 "2026-04-22T18:54:22Z")

</div>

Personally Identifiable information (PII)

---

<div class="post-metadata">

**Author:** ![Robertcarlos](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/robertcarlos/32/760222_2.png) [@Robertcarlos](https://community.openai.com/u/Robertcarlos)\
**Post date:** [September 18, 2026, 2:27am UTC](https://community.openai.com/t/openai-privacy-filter-for-detecting-and-masking-pii-in-text/1379537/3 "2026-09-18T02:27:36Z")

</div>

The local deployment and fine-tuning options make this interesting for applications where sensitive text can’t be sent to an external service. The 128k context window also seems useful for filtering larger documents without splitting them into smaller chunks.