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: Jul 12, 2026, 1:03 AM
Fully verified Every check passed its required attestation, channel, and provenance gates.
8 verified 0 partial 0 failed 0 unavailable
Hardware 8/8 good Freshness Not shown Key binding 8/8 good Workload 8/8 good Provenance 8/8 good Availability 8/8 good
Gemma 4 31b Attested E2EE Details Gemma Latest Attested E2EE Details Gpt Oss 120b Attested E2EE Details Gpt Oss Latest Attested E2EE Details Kimi K2.6 Attested E2EE Details Qwen3 Embedding 4b Attested E2EE Details Voxtral Mini 3b Attested E2EE Details Whisper Large V3 Attested E2EE Details
Get notified when this provider's attestation verdict changes:
Alerts RSS
Models & Pricing
| Model | Family | Context | Max Out | Input /M | Output /M | Free |
|---|---|---|---|---|---|---|
| GPT-OSS 120B | OpenAI GPT | 128K | — | $0.49 | $1.94 | — |
| Whisper Large v3 | OpenAI GPT | 29K | — | €0.014/min audio | — | — |
| Kimi K2.6 | Moonshot AI | 256K | — | $1.77 | $8.85 | — |
| Gemma Latest | Google Gemma | 4K | — | Custom | — | — |
| Qwen3 Embedding 4B | Qwen | 32K | — | $0.15 | $0.00 | — |
| GPT-OSS Latest | OpenAI GPT | 4K | — | Custom | — | — |
| Voxtral Mini 3B | Mistral | 32K | — | €0.004/min audio | — | — |
| Gemma 4 31B | Google Gemma | 128K | — | $0.88 | $1.45 | — |