privacy-filter
Released by openai in 2026, privacy-filter is an chat model. privacy-filter is an open-weights chat model.
by openai
Best for
Ways to use privacy-filter in osFoundry
Connect with your own key (BYOK)
Open the key dialog and paste your openai API key. osFoundry discovers privacy-filter automatically — assign it to a Maestro role (router, direct, orchestrator, or fallback) in the Pipeline tab and it is live in every chat. Your key, your provider account — no token markup.
Deploy a dedicated endpoint
privacy-filter is open-weights — run it locally for free, or deploy a dedicated GPU endpoint in your workspace for reserved capacity with no rate limits.
Use it in a Room App
Room Apps declare AI features in their manifest, then call them with invokeAI:
import { invokeAI } from '@osfoundry/app-sdk'
// 'summarize' is an AI feature declared in your app manifest.
const result = await invokeAI('summarize', userText)
Call it from your own apps
Once a model is wired into your workspace you can host it as an API and reach it from your own services, scripts, or CI — outside osFoundry.
privacy-filter vs similar models
Licence
Unspecified — Licence terms not specified — verify the upstream model card before commercial use.
Check upstream documentation.
Frequently asked about privacy-filter
Is privacy-filter free to use?
privacy-filter is free to run locally on your own hardware. Hosted access through osFoundry is metered (input Free (local), output Free (local)). You can switch between local and hosted at any time.
Can I use privacy-filter commercially?
Commercial use is allowed with conditions. Licence terms not specified — verify the upstream model card before commercial use. Check upstream documentation.
Can I run privacy-filter locally?
Yes. privacy-filter is open-weights and runs locally on a workstation GPU. osFoundry's local runtime handles model loading, quantisation, and routing.
What is privacy-filter best at?
privacy-filter is well-suited to token classification.
How do I use privacy-filter in osFoundry?
Paste your openai API key in the key dialog (or deploy the open weights for self-hostable models), assign privacy-filter to a Maestro role in the Pipeline tab, then use it in chat, Room Apps via invokeAI, or your own apps.
Published by openai on April 17, 2026. Source: https://huggingface.co/openai/privacy-filter