Privatemode
Attested E2EEEU-hosted confidential inference via Cosmian VM
Privatemode delivers privacy-first AI inference from EU data centers using Cosmian VM — a hardened confidential VM combining AMD SEV-SNP and Intel TDX. Accessed via a local proxy binary, the service is designed for GDPR-sensitive workloads where data must remain within a cryptographically isolated enclave throughout processing.
API Features
OpenAI Compatible ✓
Streaming ✓
Function Calling —
Batch Inference —
Vision ✓
Embeddings ✓
Attestation Status
View full details →Last checked: Jun 18, 2026, 11:05 AM
Fully verified Every check passed its required attestation, channel, and provenance gates.
6 verified 0 partial 0 failed 0 unavailable
Hardware 6 bad Freshness Not shown Key binding Not shown Workload Not shown Provenance 6/6 good Availability 6/6 good
Models & Pricing
| Model | Family | Context | Max Out | Input /M | Output /M | Free |
|---|---|---|---|---|---|---|
| Whisper Large v3 | OpenAI GPT | 29K | — | €0.014/min audio | — | — |
| Voxtral Mini 3B | Mistral | 32K | — | €0.004/min audio | — | — |
| Qwen3 Embedding 4B | Qwen | 32K | — | $0.15 | $0.00 | — |
| Kimi K2.6 | Moonshot AI | 256K | — | $1.80 | $9.01 | — |
| Gemma 4 31B | Google Gemma | 128K | — | $0.90 | $1.48 | — |
| GPT-OSS 120B | OpenAI GPT | 128K | — | $0.50 | $1.98 | — |