Check inference deployment quota

Check if global quota is exceeded, if yes the number of additional quotas needed to create the specified inference deployment will be calculated.

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

Check inference deployment quota

cURL

curl --request POST \
  --url https://api.gcore.com/cloud/v3/inference/{project_id}/deployments/check_limits \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "containers": [
    {
      "region_id": 1,
      "scale": {
        "max": 3,
        "min": 1
      }
    }
  ],
  "flavor_name": "inference-16vcpu-232gib-1xh100-80gb"
}
'

import requests

url = "https://api.gcore.com/cloud/v3/inference/{project_id}/deployments/check_limits"

payload = {
    "containers": [
        {
            "region_id": 1,
            "scale": {
                "max": 3,
                "min": 1
            }
        }
    ],
    "flavor_name": "inference-16vcpu-232gib-1xh100-80gb"
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    containers: [{region_id: 1, scale: {max: 3, min: 1}}],
    flavor_name: 'inference-16vcpu-232gib-1xh100-80gb'
  })
};

fetch('https://api.gcore.com/cloud/v3/inference/{project_id}/deployments/check_limits', 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/{project_id}/deployments/check_limits",
  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([
    'containers' => [
        [
                'region_id' => 1,
                'scale' => [
                                'max' => 3,
                                'min' => 1
                ]
        ]
    ],
    'flavor_name' => 'inference-16vcpu-232gib-1xh100-80gb'
  ]),
  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;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.gcore.com/cloud/v3/inference/{project_id}/deployments/check_limits"

	payload := strings.NewReader("{\n  \"containers\": [\n    {\n      \"region_id\": 1,\n      \"scale\": {\n        \"max\": 3,\n        \"min\": 1\n      }\n    }\n  ],\n  \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.gcore.com/cloud/v3/inference/{project_id}/deployments/check_limits")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"containers\": [\n    {\n      \"region_id\": 1,\n      \"scale\": {\n        \"max\": 3,\n        \"min\": 1\n      }\n    }\n  ],\n  \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"containers\": [\n    {\n      \"region_id\": 1,\n      \"scale\": {\n        \"max\": 3,\n        \"min\": 1\n      }\n    }\n  ],\n  \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\"\n}"

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

200

{
  "inference_cpu_millicore_count_limit": 8000,
  "inference_cpu_millicore_count_requested": 3000,
  "inference_cpu_millicore_count_usage": 2000,
  "inference_gpu_a100_count_limit": 4,
  "inference_gpu_a100_count_requested": 2,
  "inference_gpu_a100_count_usage": 1,
  "inference_gpu_h100_count_limit": 4,
  "inference_gpu_h100_count_requested": 2,
  "inference_gpu_h100_count_usage": 1,
  "inference_gpu_l40s_count_limit": 4,
  "inference_gpu_l40s_count_requested": 2,
  "inference_gpu_l40s_count_usage": 1,
  "inference_instance_count_limit": 10,
  "inference_instance_count_requested": 1,
  "inference_instance_count_usage": 1
}

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

containers · ContainerInSerializerV3 · object[] · required

List of containers for the inference instance.

Minimum array length: 1

Show child attributes

Example:

[
  {
    "region_id": 1,
    "scale": { "max": 3, "min": 1 }
  }
]

flavor_name · string · required

Inference flavor name.

Minimum string length: 1

Example:

"inference-16vcpu-232gib-1xh100-80gb"

Response

200 - application/json

OK

inference_cpu_millicore_count_limit · integer

Inference CPU millicore count limit

Example:

8000

inference_cpu_millicore_count_requested · integer

Inference CPU millicore count requested

Example:

3000

inference_cpu_millicore_count_usage · integer

Inference CPU millicore count usage

Example:

2000

inference_gpu_a100_count_limit · integer

Inference GPU A100 Count limit

Example:

4

inference_gpu_a100_count_requested · integer

Inference GPU A100 Count requested

Example:

2

inference_gpu_a100_count_usage · integer

Inference GPU A100 Count usage

Example:

1

inference_gpu_h100_count_limit · integer

Inference GPU H100 Count limit

Example:

4

inference_gpu_h100_count_requested · integer

Inference GPU H100 Count requested

Example:

2

inference_gpu_h100_count_usage · integer

Inference GPU H100 Count usage

Example:

1

inference_gpu_l40s_count_limit · integer

Inference GPU L40s Count limit

Example:

4

inference_gpu_l40s_count_requested · integer

Inference GPU L40s Count requested

Example:

2

inference_gpu_l40s_count_usage · integer

Inference GPU L40s Count usage

Example:

1

inference_instance_count_limit · integer

Inference instance count limit

Example:

10

inference_instance_count_requested · integer

Inference instance count requested

Example:

1

inference_instance_count_usage · integer

Inference instance count usage

Example:

1