OpenRelay adds dedicated GPU VMs and usage-based inference
Added “OpenRelay: Hosted inference and GPU compute”; “OpenRelay provides hosted model inference and dedicated GPU VMs, with per-token and usage-based pricing.”; “Hosted inferenceand GPU compute.”. Removed “OpenRelay — Distributed GPU cloud for production inference”; “OpenRelay runs production inference across a distributed network of GPUs — up to 90% cheaper than AWS, Azure, and GCP, with automatic failover built in.”; “The compute layerfor AI applications.”.
WHY IT MAY MATTER
Positioning source · structured before/after evidence ↗A packaging or usage-policy change can alter effective price, product eligibility, and customer comparisons.