Delete Model Endpoints

DELETE

/serving/inference/{inference_id}/

curl --request DELETE \
  --url 'https://api.e2enetworks.com/myaccount/api/v1/gpu/serving/inference/{inference_id}/?project_id=<PROJECT_ID>&location=<LOCATION>&apikey=<API_KEY>' \
  --header 'Authorization: Bearer <API_TOKEN>'

Parameters

Path Parameters

inference_id

required

integer

Query Parameters

project_id

required

integer

Project ID

active_iam

integer

Active IAM ID (To access contact person account) Find your Active IAM ID here

location

required

string

Allowed values: Delhi Chennai

Location

Responses

200

Model endpoint details retrieved successfully

Media typeapplication/json

object

code

integer

data

object

id

integer

model

object

dataset

object

model_type

object

sku

integer

name

string

storage_url

string

nullable

dataset_storage_url

string

nullable

status

string

created_by

object

id

integer

name

string

email

string

username

string

created_at

string format: date-time

updated_at

string format: date-time

detailed_info

object

args

Array<string>

commands

Array<string>

info_log

boolean

error_log

boolean

tokenizer

string

world_size

integer

warning_log

boolean

server_version

string

hugging_face_id

string

model_serve_type

string

log_verbose_level

integer

replica

integer

framework

string

custom_endpoint_details

object

container

object

advance_config

object

liveness_probe

object

key

additional properties

any

readiness_probe

object

path

string

port

string

protocol

string

period_seconds

integer

timeout_seconds

integer

failure_threshold

integer

success_threshold

integer

initial_delay_seconds

integer

image_pull_policy

string

is_liveness_probe_enabled

boolean

is_readiness_probe_enabled

boolean

container_name

string

container_type

string

private_image_details

object

public_ip

string

resource_details

object

disk_size

integer

mount_path

string

env_variables

Array<string>

message

string

auto_scale_policy

object

min_replicas

integer

max_replicas

integer

rules

Array<object>

object

value

integer

metric

string

window

integer

granularity

integer

watch_period

integer

condition_type

string

custom_metric_name

string

stability_period

string

is_auto_scale_enabled

boolean

desired_replica

integer

model_load_integration_id

integer

sku_details

object

specs

object

sku_id

integer

name

string

series

string

cpu

integer

gpu

integer

memory

integer

is_free

boolean

is_active

boolean

gpu_switch_type

string

nullable

local_storage_in_gb

integer

plan

object

sku_item_price_id

integer

sku_type

string

committed_days

integer

unit_price

number format: float

currency

string

is_active

boolean

description

string

committed_info

object

committed_replicas

integer

private_cloud_id

object

custom_sku

object

errors

object

message

string

Example

{
  "code": 200,
  "data": {
    "id": 3035,
    "sku": 162,
    "name": "tir-endpoint-111516583333",
    "status": "Done",
    "created_by": {
      "id": 3573,
      "name": "Nipun",
      "email": "nipun.arora@e2enetworks.com",
      "username": "nipun.arora@e2enetworks.com"
    },
    "created_at": "2024-11-15T11:28:58.532961Z",
    "updated_at": "2024-11-15T11:51:05.587489Z",
    "detailed_info": {
      "info_log": true,
      "error_log": true,
      "tokenizer": "",
      "world_size": 1,
      "warning_log": true,
      "server_version": "",
      "hugging_face_id": "",
      "model_serve_type": "",
      "log_verbose_level": 1
    },
    "replica": 1,
    "framework": "stable_diffusion_xl",
    "custom_endpoint_details": {
      "container": {
        "advance_config": {
          "readiness_probe": {
            "path": "/v2/health/ready",
            "port": "8080",
            "protocol": "http",
            "period_seconds": 10,
            "timeout_seconds": 10,
            "failure_threshold": 3,
            "success_threshold": 1,
            "initial_delay_seconds": 10
          }
        },
        "image_pull_policy": "Always",
        "is_liveness_probe_enabled": false,
        "is_readiness_probe_enabled": false,
        "container_name": "registry.e2enetworks.net/aimle2e/stable-diffusion-xl-base-1.0:hf",
        "container_type": "public"
      },
      "public_ip": "no",
      "resource_details": {
        "disk_size": 100,
        "mount_path": ""
      }
    },
    "message": "",
    "auto_scale_policy": {
      "min_replicas": 1,
      "max_replicas": 1,
      "rules": [
        {
          "value": 100,
          "metric": "",
          "window": 1,
          "granularity": 1,
          "watch_period": 60,
          "condition_type": "limit",
          "custom_metric_name": ""
        }
      ],
      "stability_period": "300"
    },
    "is_auto_scale_enabled": false,
    "desired_replica": 1,
    "model_load_integration_id": 428,
    "sku_details": {
      "specs": {
        "sku_id": 162,
        "name": "GDC.1xH200-30.375GB_SXM",
        "series": "GPU",
        "cpu": 30,
        "gpu": 1,
        "memory": 375,
        "is_free": false,
        "is_active": true,
        "local_storage_in_gb": 0
      },
      "plan": {
        "sku_item_price_id": 755,
        "sku_type": "hourly",
        "committed_days": 0,
        "unit_price": 470.4,
        "currency": "INR",
        "is_active": true,
        "description": "Hourly Compute Instance: inference_service"
      }
    },
    "committed_replicas": 0
  },
  "message": "Success"
}