List serverless endpoint workers

Returns the active workers for a serverless endpoint plus a summary of worker counts. Each worker’s status is derived by reconciling the worker pod’s lifecycle status with the endpoint’s live job-queue view. When the job-queue view is unavailable the response degrades to the pod-derived status and counts.

GET /v2/serverless/{id}/workers

Error

A valid request URL is required to generate request examples

200

{
  "workers": [
    {
      "id": "worker_abc",
      "isStale": false,
      "gpuCount": 1,
      "version": 4,
      "image": "my-org/sdxl-worker:latest",
      "uptimeSeconds": 3600,
      "gpuTypeId": "NVIDIA RTX 4090",
      "dataCenterId": "US-TX-3",
      "startedAt": "2026-03-26T00:00:00Z"
    }
  ],
  "summary": {
    "running": 2,
    "idle": 1,
    "initializing": 0,
    "throttled": 0,
    "unhealthy": 0,
    "total": 3
  },
  "endpointVersion": 4
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

id · string · required

Serverless endpoint identifier

Response

200

application/json

OK

workers · object[] · required

Show child attributes

summary · object · required

Histogram of the returned workers by status. The per-status counts are a roll-up of the workers array, so running + idle + initializing + throttled + unhealthy == total == len(workers).

Show child attributes

endpointVersion · integer | null

The endpoint's current configuration version. A worker whose version differs is running stale config (see worker.isStale). Null if unknown.

Example:

4