Skip to content
OpenRelay is in early access, and the /v1 API is stable. New capabilities ship in the changelog.
API ReferencePricingDashboard
Catalog

GPU availability by model

Live availability per GPU model. Responses are served from a short-lived cache.

GET
/v1/gpu-availability

Authorization

apiKey
AuthorizationBearer <token>

OpenRelay API key. Send it as Authorization: Bearer vl_….

In: header

Response Body

application/json

application/json

application/json

curl -X GET "https://example.com/v1/gpu-availability"
[
  {
    "gpuModelId": "rtx-4090",
    "vm": {
      "totalGpus": 12,
      "freeGpus": 5,
      "maxPlaceableGpus": 4
    },
    "cluster": {
      "totalGpus": 8,
      "freeGpus": 8,
      "maxPlaceableGpus": 8
    }
  }
]
{
  "error": "string",
  "code": "string"
}
{
  "error": "string",
  "code": "string"
}

Command line

The orl CLI wraps this endpoint:

orl catalog gpu-availability get

List models in the OpenRelay catalog (OpenAI-compatible) GET

Returns the public model catalog. Free, not balance-gated. Models with status "available" can be used immediately in /v1/chat/completions; "request_access" models are listed for discovery but are not yet invocable.

GPU model catalog GET

Next Page