Get Endpoint

GET 
/inference/endpoints/:id

Get Endpoint by ID

Request

Path Parameters

id stringrequired

495695b9-088d-4f49-823a-e6bb5b3a709e

Responses

200

OK

application/json

Schema

Schema

currentReplicas integer

Replicas current count

exampleCommand string

Example command to use the endpoint

gpuCount integer

Number of GPUs

gpuType string

Type of GPU

hourlyPrice number

Hourly price

id string

ID of the endpoint

locationName string

Name of the Location where the Endpoint is hosted

maxReplicas integer

Replicas max count

minReplicas integer

Replicas min count

modelName string

Model Name

name string

Name of the endpoint

replicas

object[]

Replicas

Array [

gpus integer

Gpus used by the replica

status string

Status of the replica

]

scaleToZeroRetentionPeriodSeconds integer

ScaleToZeroRetentionPeriod in seconds

status string

Status of the endpoint

url string

Url of the endpoint

Example (from schema)

{
  "currentReplicas": 1,
  "exampleCommand": "curl -X POST -H 'Content-Type: application/json' -d '{\"data\": [1, 2, 3]}' https://example.com",
  "gpuCount": 1,
  "gpuType": "L4",
  "hourlyPrice": 0.5,
  "id": "1190bae6-12ab-4e6e-b7bc-3d9e6ef3cf6f",
  "locationName": "lille-4",
  "maxReplicas": 1,
  "minReplicas": 1,
  "modelName": "some-sku",
  "name": "my-endpoint",
  "replicas": [
    {
      "gpus": 1,
      "status": "Running"
    }
  ],
  "scaleToZeroRetentionPeriodSeconds": 1800,
  "status": "Available",
  "url": "https://example.com"
}

Loading...