LLM Reference

OpenAI Privacy Filter Models by OpenAI

OpenAIApache 2.0Open source
1 model2026Up to 128k ctx

Last refreshed 2026-04-23. Next refresh: weekly.

Details

ResearcherOpenAI
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2026
Max context128k

About

OpenAI's open-weight privacy and PII detection model family, released for local text redaction and data minimization workflows.

Decision facts

Best fit
safety
Capability starting point
OpenAI Privacy Filter with 128k context
Lowest tracked input
Not tracked
Closest related family
GPT Realtime 2

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

1 in view

Use when the workload needs safety, 128k context, and 1.5B parameters.

2026-04safety128k context1.5B parameters

Release Timeline

1 release group
2026-04
1 current
OpenAI Privacy Filter
safety128k context1.5B parameters
Current

Specifications(1 models)

OpenAI Privacy Filter model specifications comparison
ModelReleasedContextParameters
OpenAI Privacy Filter2026-04128k1.5B