Moderation and safetyText analysis

OpenAI Privacy Filter

Finds and hides personal data: names, addresses, phone numbers, emails, account numbers, passwords. Runs even in the browser. Trained mostly on English.

Developer
OpenAI, USA
First release
Apr 2026
Latest release
Apr 2026
Sizes
1.5B (50M active)
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Security, Legal, Documents and accounting
Deploy on your server Hugging Face GitHub

What it does

  • Removing personal data from text before sending it to cloud AI
  • Finding passwords and keys in texts
  • Anonymizing correspondence for analytics

Where it is used

Information securityCustomer supportLegal departments

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Privacy Filter

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can OpenAI Privacy Filter be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does OpenAI Privacy Filter need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does OpenAI Privacy Filter support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download OpenAI Privacy Filter and what does it cost?

The OpenAI Privacy Filter weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Moderation and safetyGLiNER-PIIGLiNER community (Fastino, Knowledgator, NVIDIA and others) · USACommercial use allowed

Small GLiNER-based models for finding personal data: passports, phone numbers, accounts, addresses. Data types are set in words. Russian is not officially supported.

DetailsModeration and safetyPiiranhaiiiorg · not disclosedNon-commercial only

A popular detector of 17 types of personal data in six European languages. No Russian and a non-commercial license: suitable for trials and research.

DetailsText analysisGLiNERUrchade Zaratiana and Fastino AI · France / USACommercial use allowed

Finds the entities you need in text without training: just list what to look for (name, amount, date). GLiNER2 also classifies text. Multilingual versions understand Russian.

Details

Source: huggingface.co/openai/privacy-filter. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.