On-demand cloud GPUs and OpenAI-compatible inference billed hourly with no commitment, quota, or reservation.
OpenRelay provides on-demand GPU virtual machines and an OpenAI-compatible inference gateway with per-hour billing and no upfront commitments. Users can deploy a GPU VM in minutes or redirect an existing OpenAI integration with a one-line base URL change. Community tier GPU options range from NVIDIA RTX 3090 at $0.18/hr to H200 at $3.20/hr. OpenRelay also enables inference providers to list their capacity on the platform. OpenRelay is a product of OpenRelay.