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

Get a dedicated endpoint

Returns one of your dedicated endpoints: the model id to send in inference requests, its status, whether it is enabled, and its per-token pricing.

Required permission

Requires the endpoint.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 get <id>
GET
/v1/inference/endpoints/{id}

Authorization

apiKey
headerAuthorizationBearer <token>

OpenRelay API key. Send it as Authorization: Bearer or_… (legacy vl_… keys still work).

Path Parameters

id*string

Response Body

Endpoint

application/json
  1. response

A dedicated endpoint as its organization sees it.

id*string
orgId*string
name*string
modelId*string

the model id to send as model in inference requests

modality*string
status*string
statusReason?string
enabled*boolean

false while the endpoint is disabled: inference requests to it return 404

pricingNanoUSD*

the endpoint's price per token by usage dimension, in nanoUSD (1e-9 USD)

version*integer
Formatint64
createdAt*string
updatedAt*string
Example Request
curl -X GET 'https://api.openrelay.inc/v1/inference/endpoints/string'
Example Response
{  "id": "string",  "orgId": "string",  "name": "string",  "modelId": "string",  "modality": "string",  "status": "string",  "statusReason": "string",  "enabled": true,  "pricingNanoUSD": {    "property1": 0,    "property2": 0  },  "version": 0,  "createdAt": "string",  "updatedAt": "string"}