Update inference application deployment
curl --request PATCH \
--url https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name} \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"api_keys": [
"key1",
"key2"
],
"components_configuration": {
"model": {
"scale": {
"max": 2
}
}
},
"regions": [
1,
2
]
}
'import requests
url = "https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
payload = {
"api_keys": ["key1", "key2"],
"components_configuration": { "model": { "scale": { "max": 2 } } },
"regions": [1, 2]
}
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.patch(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'PATCH',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
api_keys: ['key1', 'key2'],
components_configuration: {model: {scale: {max: 2}}},
regions: [1, 2]
})
};
fetch('https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}', 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/{deployment_name}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "PATCH",
CURLOPT_POSTFIELDS => json_encode([
'api_keys' => [
'key1',
'key2'
],
'components_configuration' => [
'model' => [
'scale' => [
'max' => 2
]
]
],
'regions' => [
1,
2
]
]),
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/applications/{project_id}/deployments/{deployment_name}"
payload := strings.NewReader("{\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"components_configuration\": {\n \"model\": {\n \"scale\": {\n \"max\": 2\n }\n }\n },\n \"regions\": [\n 1,\n 2\n ]\n}")
req, _ := http.NewRequest("PATCH", 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.patch("https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"components_configuration\": {\n \"model\": {\n \"scale\": {\n \"max\": 2\n }\n }\n },\n \"regions\": [\n 1,\n 2\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Patch.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"components_configuration\": {\n \"model\": {\n \"scale\": {\n \"max\": 2\n }\n }\n },\n \"regions\": [\n 1,\n 2\n ]\n}"
response = http.request(request)
puts response.read_body{
"tasks": [
"d478ae29-dedc-4869-82f0-96104425f565"
]
}Everywhere Inference Apps
Update inference application deployment
Updates an existing application deployment. You can modify the target regions and update configurations for individual components. To disable a component, set its value to null. Only the provided fields will be updated; all others remain unchanged.
PATCH
/
cloud
/
v3
/
inference
/
applications
/
{project_id}
/
deployments
/
{deployment_name}
Update inference application deployment
curl --request PATCH \
--url https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name} \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"api_keys": [
"key1",
"key2"
],
"components_configuration": {
"model": {
"scale": {
"max": 2
}
}
},
"regions": [
1,
2
]
}
'import requests
url = "https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
payload = {
"api_keys": ["key1", "key2"],
"components_configuration": { "model": { "scale": { "max": 2 } } },
"regions": [1, 2]
}
headers = {
"Authorization": "<api-key>",
"Content-Type": "application/json"
}
response = requests.patch(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'PATCH',
headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
body: JSON.stringify({
api_keys: ['key1', 'key2'],
components_configuration: {model: {scale: {max: 2}}},
regions: [1, 2]
})
};
fetch('https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}', 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/{deployment_name}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "PATCH",
CURLOPT_POSTFIELDS => json_encode([
'api_keys' => [
'key1',
'key2'
],
'components_configuration' => [
'model' => [
'scale' => [
'max' => 2
]
]
],
'regions' => [
1,
2
]
]),
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 $response;
}package main
import (
"fmt"
"strings"
"net/http"
"io"
)
func main() {
url := "https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}"
payload := strings.NewReader("{\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"components_configuration\": {\n \"model\": {\n \"scale\": {\n \"max\": 2\n }\n }\n },\n \"regions\": [\n 1,\n 2\n ]\n}")
req, _ := http.NewRequest("PATCH", url, payload)
req.Header.Add("Authorization", "<api-key>")
req.Header.Add("Content-Type", "application/json")
res, _ := http.DefaultClient.Do(req)
defer res.Body.Close()
body, _ := io.ReadAll(res.Body)
fmt.Println(string(body))
}HttpResponse<String> response = Unirest.patch("https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"components_configuration\": {\n \"model\": {\n \"scale\": {\n \"max\": 2\n }\n }\n },\n \"regions\": [\n 1,\n 2\n ]\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.gcore.com/cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Patch.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"components_configuration\": {\n \"model\": {\n \"scale\": {\n \"max\": 2\n }\n }\n },\n \"regions\": [\n 1,\n 2\n ]\n}"
response = http.request(request)
puts response.read_body{
"tasks": [
"d478ae29-dedc-4869-82f0-96104425f565"
]
}Authorizations
API key for authentication. Make sure to include the word apikey, followed by a single space and then your token.
Example: apikey 1234$abcdef
Path Parameters
Project ID
Example:
1
Name of deployment
Body
application/json
List of API keys for the application
Example:
["key1", "key2"]
Mapping of component names to their configuration (e.g., "model": {...})
Show child attributes
Show child attributes
Examples:
{ "model": { "scale": { "max": 2 } } }
{
"model": {
"flavor": "inference-16vcpu-232gib-1xh100-80gb"
}
}
Geographical regions to be updated for the deployment
Example:
[1, 2]
Response
200 - application/json
OK
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"]
Was this page helpful?
⌘I