OpenRelay
OpenRelay is a Y Combinator-backed distributed GPU cloud for production AI inference — "the CDN of inference." It runs a global mesh of GPUs (RTX 4090/5090, A100, H100) that teams reach through a single API: rent dedicated GPU VMs with SSH and persistent volumes, stand up autoscaling inference clusters behind an endpoint, or call hosted open models via an OpenAI-compatible (and Anthropic Messages-compatible) API. Anyone can also join as a provider and earn on idle compute. The control-plane REST API (api.openrelay.inc) manages orgs, VMs, clusters, snapshots, billing, usage, transfers, provider nodes, batches, files, and webhooks, and is fully driveable from the first-party `orl` CLI — which also ships an official MCP server for agents. Traffic reroutes across healthy nodes in milliseconds, with pricing OpenRelay claims is up to 90% cheaper than the hyperscalers.
OpenRelay publishes 18 APIs on the APIs.io network, including Account API, API Keys API, Batches API, and 15 more. Tagged areas include Company, GPU, Inference, AI, and Machine Learning.
The OpenRelay catalog on APIs.io includes 1 event-driven AsyncAPI specification.
OpenRelay’s developer surface includes documentation, API reference, getting-started guide, signup flow, pricing, engineering blog, support, and 23 more developer resources.
Kin Score
APIs 19
Individual APIs this provider publishes, each with its own machine-readable definition.
OpenRelay Inference API
OpenAI-compatible chat completions API (POST /v1/chat/completions) and, for supporting models, an Anthropic-compatible Messages API (POST /v1/messages). Drop-in: point the offic...
OpenRelay Account API
The signed-in user: profile, memberships, and first-time onboarding.
OpenRelay API Keys API
Programmatic access keys (vl_…) used to authenticate with this API.
OpenRelay Batches API
Batch inference jobs: submit a JSONL file of requests, poll status, and download results at a discounted rate. Served by the inference endpoint (inference.openrelay.inc). Batch ...
OpenRelay Billing API
Prepaid balance, saved cards, deposits, and auto-recharge.
OpenRelay Catalog API
Public catalog: GPU models, availability, pricing, templates, and locations.
OpenRelay Clusters API
Autoscaling inference clusters that serve a container image behind an endpoint.
OpenRelay Files API
Input and result files for the Batch API (JSONL, up to 200 MB and 50,000 records). Served by the inference endpoint (inference.openrelay.inc).
OpenRelay Internal API
Machine-to-machine endpoints used by platform infrastructure. Not part of the public API.
OpenRelay Organizations API
Organizations and their members. Most resources are scoped to an org.
OpenRelay Provider API
For GPU providers: applications, nodes, provisioning tokens, and earnings.
OpenRelay Registry Credentials API
Private container-registry credentials for pulling images.
OpenRelay Runners API
Managed GitHub Actions runner pools.
OpenRelay Snapshots API
Point-in-time VM snapshots and forking new VMs from them.
OpenRelay SSH Keys API
Org-level SSH public keys that can be attached to VMs.
OpenRelay Transfers API
Move resources between organizations you belong to.
OpenRelay Usage API
Current-period usage and cost breakdowns.
OpenRelay VMs API
GPU virtual machines: lifecycle, disks, SSH access, and console links.
OpenRelay Webhooks API
Subscribe to platform events with signed HTTP callbacks.
Scroll for all 19
MCP Servers 1
Model Context Protocol servers that expose these APIs to AI agents.
openrelay-mcp.yml
MCP SERVEREvent Specifications 1
AsyncAPI definitions for this provider's event-driven and streaming APIs.
Openrelay Webhooks
ASYNCAPISecurity Posture 3
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Resources
Get Started 3
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 6
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 5
Authentication, authorization, and security posture
Operate 3
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
Company 1
The organization behind the API