Live pod GPU capacity and on-demand rates
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.
Command line
The orl CLI wraps this endpoint:
orl pods capacity listAuthorization
apiKey OpenRelay API key. Send it as Authorization: Bearer or_… (legacy vl_… keys still work).
In: header
Response Body
application/json
application/json
application/json
curl -X GET "https://example.com/v1/pods/capacity"{ "items": [ { "gpuModelId": "string", "name": "string", "vramGb": 0, "freeUnits": 0, "totalUnits": 0, "maxGpuCount": 0, "rateOnDemandCentsPerHour": 0, "rateReservedCentsPerHour": 0, "rateInterruptibleCentsPerHour": 0 } ]}Create a pod POST
Compute-fabric pod (BYO container image + SSH keys): a hardened GPU container on a whole native-driver GPU. Admission claims a free device-request GPU unit (see listPodCapacity for what is claimable), snapshots the on-demand rate immutably onto the pod, and drives the guest workflow.
Overview
Point-in-time VM snapshots and forking new VMs from them.