System Status
Live uptime, latency, and incident history for VoltageGPU Confidential Compute (Intel TDX GPUs), TEE Inference API, and Confidential Agents. The checks below run from our server when the page loads (refreshed every minute); the 90-day history is on our UptimeRobot board.
Monitored services
- Confidential Compute, H100, H200 and RTX PRO 6000 Blackwell in Intel TDX confidential VMs. SLA target: 99.9%.
- TEE Inference API, OpenAI-compatible endpoints at api.voltagegpu.com/v1. Requests pass through our relay, which sees them in clear (TLS ends at our host). To keep plaintext off our servers, run your own inference server in a Confidential VM and terminate TLS inside its trust domain. SLA target: 99.95%.
- Confidential Agents, pre-built agents on TEE models from our catalog (contract analysis, financial audit, etc.).
- Volt Public API, Pod / machine / template management at api.voltagegpu.com.
- Web Dashboard, app.voltagegpu.com authenticated console.
Looking for something else? Visit our home page or read the documentation.