Create inference application deployment

Creates a new application deployment based on a selected catalog application. Specify the desired deployment name, target regions, and configuration for each component. The platform will provision the necessary resources and initialize the application accordingly.

POST /cloud/v3/inference/applications/{project_id}/deployments

Python

Python

import os
from gcore import Gcore

client = Gcore(
    api_key=os.environ.get("GCORE_API_KEY"),  # This is the default and can be omitted
)
task_id_list = client.cloud.inference.applications.deployments.create(
    project_id=1,
    application_name="demo-app",
    components_configuration={
        "model": {
            "exposed": True,
            "flavor": "inference-16vcpu-232gib-1xh100-80gb",
            "scale": {
                "max": 1,
                "min": 1,
            },
        }
    },
    name="name",
    regions=[1, 2],
)
print(task_id_list.tasks)

package main

import (
	"context"
	"fmt"

	"github.com/G-Core/gcore-go"
	"github.com/G-Core/gcore-go/cloud"
	"github.com/G-Core/gcore-go/option"
)

func main() {
	client := gcore.NewClient(
		option.WithAPIKey("My API Key"),
	)
	taskIDList, err := client.Cloud.Inference.Applications.Deployments.New(context.TODO(), cloud.InferenceApplicationDeploymentNewParams{
		ProjectID:       gcore.Int(1),
		ApplicationName: "demo-app",
		ComponentsConfiguration: map[string]cloud.InferenceApplicationDeploymentNewParamsComponentsConfiguration{
			"model": {
				Exposed: true,
				Flavor:  "inference-16vcpu-232gib-1xh100-80gb",
				Scale: cloud.InferenceApplicationDeploymentNewParamsComponentsConfigurationScale{
					Max: 1,
					Min: 1,
				},
			},
		},
		Name:    "name",
		Regions: []int64{1, 2},
	})
	if err != nil {
		panic(err.Error())
	}
	fmt.Printf("%+v\n", taskIDList.Tasks)
}

curl --request POST \
  --url https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "application_name": "demo-app",
  "components_configuration": {
    "model": {
      "exposed": true,
      "flavor": "inference-16vcpu-232gib-1xh100-80gb",
      "scale": {
        "max": 1,
        "min": 1
      }
    }
  },
  "name": "my-app-deployment",
  "regions": [
    1,
    2
  ],
  "api_keys": [
    "key1",
    "key2"
  ]
}
'

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    application_name: 'demo-app',
    components_configuration: {
      model: {
        exposed: true,
        flavor: 'inference-16vcpu-232gib-1xh100-80gb',
        scale: {max: 1, min: 1}
      }
    },
    name: 'my-app-deployment',
    regions: [1, 2],
    api_keys: ['key1', 'key2']
  })
};

fetch('https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'application_name' => 'demo-app',
    'components_configuration' => [
        'model' => [
                'exposed' => true,
                'flavor' => 'inference-16vcpu-232gib-1xh100-80gb',
                'scale' => [
                                'max' => 1,
                                'min' => 1
                ]
        ]
    ],
    'name' => 'my-app-deployment',
    'regions' => [
        1,
        2
    ],
    'api_keys' => [
        'key1',
        'key2'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

HttpResponse<String> response = Unirest.post("https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"application_name\": \"demo-app\",\n  \"components_configuration\": {\n    \"model\": {\n      \"exposed\": true,\n      \"flavor\": \"inference-16vcpu-232gib-1xh100-80gb\",\n      \"scale\": {\n        \"max\": 1,\n        \"min\": 1\n      }\n    }\n  },\n  \"name\": \"my-app-deployment\",\n  \"regions\": [\n    1,\n    2\n  ],\n  \"api_keys\": [\n    \"key1\",\n    \"key2\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"application_name\": \"demo-app\",\n  \"components_configuration\": {\n    \"model\": {\n      \"exposed\": true,\n      \"flavor\": \"inference-16vcpu-232gib-1xh100-80gb\",\n      \"scale\": {\n        \"max\": 1,\n        \"min\": 1\n      }\n    }\n  },\n  \"name\": \"my-app-deployment\",\n  \"regions\": [\n    1,\n    2\n  ],\n  \"api_keys\": [\n    \"key1\",\n    \"key2\"\n  ]\n}"

response = http.request(request)
puts response.read_body

200

{
  "tasks": [
    "d478ae29-dedc-4869-82f0-96104425f565"
  ]
}

Authorizations

Authorization · string · header · required

API key for authentication. Make sure to include the word apikey, followed by a single space and then your token. Example: apikey 1234$abcdef

Path Parameters

project_id · integer · required

Project ID

Example:

1

Body

application/json

application_name · string · required

Identifier of the application from the catalog

Example:

"demo-app"

components_configuration · Components Configuration · object · required

Mapping of component names to their configuration (e.g., "model": {...})

Show child attributes

Example:

{
  "model": {
    "exposed": true,
    "flavor": "inference-16vcpu-232gib-1xh100-80gb",
    "scale": { "max": 1, "min": 1 }
  }
}

name · string · required

Desired name for the new deployment

Maximum string length: 15

Example:

"my-app-deployment"

regions · integer[] · required

Geographical regions where the deployment should be created

Example:

[1, 2]

api_keys · string[]

List of API keys for the application

Example:

["key1", "key2"]

Response

200 - application/json

OK

tasks · string[] · required

List of task IDs representing asynchronous operations. Use these IDs to monitor operation progress:

• GET /v1/tasks/{task_id} - Check individual task status and details Poll task status until completion (FINISHED/ERROR) before proceeding with dependent operations.

Example:

["d478ae29-dedc-4869-82f0-96104425f565"]