Get a dedicated endpoint's usage for a month
A dedicated endpoint's GPU-hours and their cost for one calendar month (UTC), read from the usage records its monthly bill is settled from. It reports the GPU-hours the endpoint's replicas were hosted, the GPU-hours of those that were billed (a replica is billed while it answers requests), and their cost in cents. The current month runs to now. A deleted endpoint's usage stays readable for the months it has records in. It is a billing read: it needs the usage permission, as the organization's usage routes do. Requests to the endpoint are not charged per token, so this is the endpoint's whole cost. It is rounded once for the endpoint, and the bill once for the organization, so the two can differ by under a cent per endpoint.
Required permission
Requires the usage.read permission. See Permissions for the roles and API key permissions that include it.
Command line
The orl CLI wraps this endpoint:
orl dedicated-endpoints usage get <id>apiKeyAuthorizationBearer <token>OpenRelay API key. Send it as Authorization: Bearer or_… (legacy vl_… keys still work).
id*stringmonth?stringThe month, as YYYY-MM in UTC; the current month when omitted.
^[0-9]{4}-(0[1-9]|1[0-2])$Usage
application/json- response
A dedicated endpoint's usage for one month, from its replicas' usage records.
endpointId*stringmonth*stringthe month, YYYY-MM in UTC
from*stringthe month's start
date-timethrough*stringthe end of the window read: the month's end, or now for the current month
date-timegpuHours*numberGPU-hours the endpoint's replicas were hosted, billed or not
doublebilledGpuHours*numberGPU-hours of replicas while they answered, the ones the endpoint is charged for
doublecents*integerthe cost of billedGpuHours at the replicas' locked rates, in cents, rounded once
int64curl -X GET 'https://api.openrelay.inc/v1/inference/endpoints/string/usage'{ "endpointId": "de_6vsr3m1k0p9t2c4x8n5w7q2z1a", "month": "2026-10", "from": "2026-10-01T00:00:00Z", "through": "2026-10-27T13:05:00Z", "gpuHours": 412.5, "billedGpuHours": 398.25, "cents": 238950}Get a dedicated endpoint's monitoring series GET
Requests, error rate, latency and time-to-first-token percentiles, and tokens for a dedicated endpoint over 1h, 6h, 24h, or 7d, on one time grid. Every series also carries a whole-range figure. This is what the dashboard's Monitoring tab shows. Data appears within a minute of the endpoint serving its first request. The example cuts each `values` array to its first three points; a `1h` response has 241.
Overview
The credentials that imports of your own model weights read private Hugging Face, S3 and Google Cloud Storage sources with, for dedicated endpoints. Without dedicated inference these return 404.