endpoints
Worker List

2min
You can use the /get_endpoint_workers/ and /get_autogroup_workers/ endpoints to get a list of workers under an endpoint group and autoscaling group respectively. Both of these endpoints take an ID. You must include your API key either in the headers as a bearer token or in the payload with key "api_token".
Example payload:
JSON
{
  "id": 123,
  "api_key": "$API_KEY"
}
{
  "id": 123,
  "api_key": "$API_KEY"
}
﻿
These values are returned:
cur_load: Current number of tokens worker is receiving per second
cur_load_rolling_avg: Rolling average of cur_load
cur_perf:
disk_usage: Storage used by instance(in Gb)
dlperf: Measured DLPerf of the instance
id: Instance ID
loaded_at: Unix epoch time the instance finished loading
measured_perf: Benchmarked performances (tokens/s). Set to DLPerf if instance is not
benchmarked yet
perf: measured_perf * reliability
reliability: Uptime of the instance, ranges 0-1
reqs_working: Number of active requests currently being processed by the instance
status: Status of the worker, can be: (
starting,
loading,
running,
idle,
stop_queued,
stopping,
stopped,
unavail,
error,
)
Example response:
JSON
[
  {
    "cur_load": 150,
    "cur_load_rolling_avg": 50,
    "cur_perf": 80,
    "disk_usage": 30,
    "dlperf": 105.87206734930771,
    "id": 123456,
    "loaded_at": 1724275993.997,
    "measured_perf": 105.87206734930771,
    "perf": 100.5784639818423245,
    "reliability": 0.95,
    "reqs_working": 2,
    "status": "running"
  }
]
[
  {
    "cur_load": 150,
    "cur_load_rolling_avg": 50,
    "cur_perf": 80,
    "disk_usage": 30,
    "dlperf": 105.87206734930771,
    "id": 123456,
    "loaded_at": 1724275993.997,
    "measured_perf": 105.87206734930771,
    "perf": 100.5784639818423245,
    "reliability": 0.95,
    "reqs_working": 2,
    "status": "running"
  }
]
﻿
﻿
Updated 16 Jan 2025
Did this page help you?
Logs