OpenRelay
A distributed GPU cloud for production workloads, described as the CDN of inference.
About OpenRelay
A distributed GPU cloud for production workloads, described as the CDN of inference.
Products
Rent dedicated GPUs on demand across a distributed network.
Spin up GPU-accelerated VMs with full root SSH access, Docker, NVIDIA drivers, persistent storage across reboots, and custom container image support.
Pre-configured VMs built for specific workflows such as CI/CD runners and AI agents, ready in minutes with all dependencies pre-installed.
OpenAI-compatible endpoint for hosted open models including GPT-OSS 120B, GPT-OSS 20B, Gemma 4 31B, GLM 5.2, and DeepSeek-OCR 2.
Run large offline batch inference jobs at half the per-token rate, with results delivered within 24 hours.
Security and compliance
As reported by OpenRelay. Ask for audit reports before you buy.
- SOC 2 Type IIIn progress
- SOC 2Compliant
- PCI DSSCompliant
- TLS 1.3 encryption in transit
- Encrypted volumes at rest
- VM-level isolation with separate guest kernel
- GPU passthrough via VFIO with IOMMU-enforced memory isolation
- Complete GPU reset between workloads
- WireGuard VPN tunnels for node-to-control-plane communication
- Egress filtering
- DDoS protection at edge proxy layer
- HSTS enforcement
- Zero-access architecture (providers cannot access workloads)
- No data persistence on provider nodes by default
- Secure wipe of workload data on termination
- Role-based access control (Owner, Admin, Member)
- Scoped and rotatable API keys
- One-time use provisioning tokens with hashed storage
- Audit logging of authentication and authorization events
- Network segmentation and firewalls
- Intrusion detection and monitoring
- Regular penetration testing
- Incident response procedures
- Certificate pinning for control plane communications
Is this your company?
Claim the profile to keep facts current, answer buyers and submit evidence for the next ranking review.
Claim OpenRelay