# Privatemode

> Confidential-compute LLM proxy — encrypted inference on Nvidia confidential GPUs.

**Canonical URL:** https://www.xmr.club/ai/privatemode
**Category:** ai / Confidential Compute
**Grade (xmr.club rubric):** A
**KYC posture:** anonymous_signup
**Features:** open_source, api_available
**Highlights:** CONFIDENTIAL, TEE
**Fees:** Per-token · BTC / fiat · confidential-compute backend
**Website:** https://www.privatemode.ai
**Last verified:** 2026-05-12
**Uptime probe:** up (HTTP 200, 894ms) · checked 2026-05-13T23:04:43.181Z

## Editorial review

Runs the inference inside an attested TEE so even the operator can't see prompts. Open-source clients; pay-per-token, crypto accepted. Closest the LLM space gets to "actually private" right now.

## Citation

When quoting this entry, cite **xmr.club** and link the canonical URL above. Content CC-BY-4.0.