Catalog

GPU availability by model

Changed on

Live availability per GPU model for VMs: total and free GPUs and the largest single allocation placeable right now, served from a short-lived cache. Capacity held exclusively for another organization is left out. Free GPUs released from another organization's reservation to the spot market are counted in spotFreeGpus, not freeGpus.

Requires the compute.read permission. See Permissions for the roles and API key permissions that include it.

get/v1/gpu-availability

Request

  • Base URL
    https://api.openrelay.inc
  • URL
    https://api.openrelay.inc/v1/gpu-availability
  • Auth
    HTTP bearer

Response

Availability by gpu model

formFactorstring

Board type, see GpuModel.formFactor. Distinguishes SKUs that share a die.

gpuModelIdstring required
namestring

Catalog display name, echoed here so a client picking from availability alone (the orl interactive picker) can show something other than a UUID.

vramGbinteger

Changes

  • 7fe59d94a9f5Revision changes
    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status

  • 12b2fcbcc298Revision changes
    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status

    • info

      added the optional property to the response with the status