Skip to content

OpenRelay is in early access, and the /v1 API is stable. New capabilities ship in the changelog.

API Reference Pricing Dashboard

API Reference Pricing Dashboard

Getting Started

Introduction Quickstart Authentication Authenticating requests to your endpoint VM billing and burn rate Pods and persistent storage Providers Provider nodes Errors Pagination

Command Line

Inference API

API Reference

Overview Create a snapshot of a VM POST List an org's VM snapshots (optionally filtered by source VM) GET Soft-delete a snapshot DELETE Fork a new VM from a snapshot POST

Snapshots

Overview

Point-in-time VM snapshots and forking new VMs from them.

Snapshots

Point-in-time VM snapshots and forking new VMs from them.

Create a snapshot of a VM

Fork a new VM from a snapshot

List an org's VM snapshots (optionally filtered by source VM)

Soft-delete a snapshot

Live pod GPU capacity and on-demand rates GET

What a pod create can actually claim right now, per GPU model: free native (device-request) GPU units on online, non-delisted nodes (the exact filter admission uses), plus the SERVER-computed on-demand hourly rate. Only models with pod units and a price are returned; a create flow should offer exactly these and render these rates verbatim rather than re-deriving prices from the catalog.

Create a snapshot of a VM POST

Beta: the snapshot record is created, but snapshot capture is not yet enabled on the data plane.

On this page