Create inference deployment
curl --request POST \
--url https://api.gcore.com/cloud/v3/inference/{project_id}/deployments \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"containers": [
{
"region_id": 1,
"scale": {
"cooldown_period": 60,
"max": 3,
"min": 1,
"triggers": {
"cpu": {
"threshold": 80
},
"memory": {
"threshold": 70
}
}
}
}
],
"flavor_name": "inference-16vcpu-232gib-1xh100-80gb",
"image": "nginx:latest",
"listening_port": 80,
"name": "my-instance",
"api_keys": [
"key1",
"key2"
],
"auth_enabled": false,
"command": [
"nginx",
"-g",
"daemon off;"
],
"credentials_name": "dockerhub",
"description": "My first instance",
"envs": {
"DEBUG_MODE": "False",
"KEY": "12345"
},
"ingress_opts": {
"disable_response_buffering": true
},
"logging": {
"destination_region_id": 1,
"enabled": true,
"retention_policy": {
"period": 42
},
"topic_name": "my-log-name"
},
"probes": {
"liveness_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
},
"readiness_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
},
"startup_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
}
},
"timeout": 120
}
'import requests
url = "https://api.gcore.com/cloud/v3/inference/{project_id}/deployments"
payload = {
"containers": [
{
"region_id": 1,
"scale": {
"cooldown_period": 60,
"max": 3,
"min": 1,
"triggers": {
"cpu": { "threshold": 80 },
"memory": { "threshold": 70 }
}
}
}
],
"flavor_name": "inference-16vcpu-232gib-1xh100-80gb",
"image": "nginx:latest",
"listening_port": 80,
"name": "my-instance",
"api_keys": ["key1", "key2"],
"auth_enabled": False,
"command": ["nginx", "-g", "daemon off;"],
"credentials_name": "dockerhub",
"description": "My first instance",
"envs": {
"DEBUG_MODE": "False",
"KEY": "12345"
},
"ingress_opts": { "disable_response_buffering": True },
"logging": {
"destination_region_id": 1,
"enabled": True,
"retention_policy": { "period": 42 },
"topic_name": "my-log-name"
},
"probes": {
"liveness_probe": {
"enabled": True,
"probe": {
"exec": { "command": ["ls", "-l"] },
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": { "Authorization": "Bearer token 123" },
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": { "port": 80 },
"timeout_seconds": 1
}
},
"readiness_probe": {
"enabled": True,
"probe": {
"exec": { "command": ["ls", "-l"] },
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": { "Authorization": "Bearer token 123" },
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": { "port": 80 },
"timeout_seconds": 1
}
},
"startup_probe": {
"enabled": True,
"probe": {
"exec": { "command": ["ls", "-l"] },
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": { "Authorization": "Bearer token 123" },
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": { "port": 80 },
"timeout_seconds": 1
}
}
},
"timeout": 120
}
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: {
cooldown_period: 60,
max: 3,
min: 1,
triggers: {cpu: {threshold: 80}, memory: {threshold: 70}}
}
}
],
flavor_name: 'inference-16vcpu-232gib-1xh100-80gb',
image: 'nginx:latest',
listening_port: 80,
name: 'my-instance',
api_keys: ['key1', 'key2'],
auth_enabled: false,
command: ['nginx', '-g', 'daemon off;'],
credentials_name: 'dockerhub',
description: 'My first instance',
envs: {DEBUG_MODE: 'False', KEY: '12345'},
ingress_opts: {disable_response_buffering: true},
logging: {
destination_region_id: 1,
enabled: true,
retention_policy: {period: 42},
topic_name: 'my-log-name'
},
probes: {
liveness_probe: {
enabled: true,
probe: {
exec: {command: ['ls', '-l']},
failure_threshold: 3,
http_get: {
port: 80,
headers: {Authorization: 'Bearer token 123'},
host: '127.0.0.1',
path: '/healthz',
schema: 'HTTP'
},
initial_delay_seconds: 0,
period_seconds: 5,
success_threshold: 1,
tcp_socket: {port: 80},
timeout_seconds: 1
}
},
readiness_probe: {
enabled: true,
probe: {
exec: {command: ['ls', '-l']},
failure_threshold: 3,
http_get: {
port: 80,
headers: {Authorization: 'Bearer token 123'},
host: '127.0.0.1',
path: '/healthz',
schema: 'HTTP'
},
initial_delay_seconds: 0,
period_seconds: 5,
success_threshold: 1,
tcp_socket: {port: 80},
timeout_seconds: 1
}
},
startup_probe: {
enabled: true,
probe: {
exec: {command: ['ls', '-l']},
failure_threshold: 3,
http_get: {
port: 80,
headers: {Authorization: 'Bearer token 123'},
host: '127.0.0.1',
path: '/healthz',
schema: 'HTTP'
},
initial_delay_seconds: 0,
period_seconds: 5,
success_threshold: 1,
tcp_socket: {port: 80},
timeout_seconds: 1
}
}
},
timeout: 120
})
};
fetch('https://api.gcore.com/cloud/v3/inference/{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/{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([
'containers' => [
[
'region_id' => 1,
'scale' => [
'cooldown_period' => 60,
'max' => 3,
'min' => 1,
'triggers' => [
'cpu' => [
'threshold' => 80
],
'memory' => [
'threshold' => 70
]
]
]
]
],
'flavor_name' => 'inference-16vcpu-232gib-1xh100-80gb',
'image' => 'nginx:latest',
'listening_port' => 80,
'name' => 'my-instance',
'api_keys' => [
'key1',
'key2'
],
'auth_enabled' => false,
'command' => [
'nginx',
'-g',
'daemon off;'
],
'credentials_name' => 'dockerhub',
'description' => 'My first instance',
'envs' => [
'DEBUG_MODE' => 'False',
'KEY' => '12345'
],
'ingress_opts' => [
'disable_response_buffering' => true
],
'logging' => [
'destination_region_id' => 1,
'enabled' => true,
'retention_policy' => [
'period' => 42
],
'topic_name' => 'my-log-name'
],
'probes' => [
'liveness_probe' => [
'enabled' => true,
'probe' => [
'exec' => [
'command' => [
'ls',
'-l'
]
],
'failure_threshold' => 3,
'http_get' => [
'port' => 80,
'headers' => [
'Authorization' => 'Bearer token 123'
],
'host' => '127.0.0.1',
'path' => '/healthz',
'schema' => 'HTTP'
],
'initial_delay_seconds' => 0,
'period_seconds' => 5,
'success_threshold' => 1,
'tcp_socket' => [
'port' => 80
],
'timeout_seconds' => 1
]
],
'readiness_probe' => [
'enabled' => true,
'probe' => [
'exec' => [
'command' => [
'ls',
'-l'
]
],
'failure_threshold' => 3,
'http_get' => [
'port' => 80,
'headers' => [
'Authorization' => 'Bearer token 123'
],
'host' => '127.0.0.1',
'path' => '/healthz',
'schema' => 'HTTP'
],
'initial_delay_seconds' => 0,
'period_seconds' => 5,
'success_threshold' => 1,
'tcp_socket' => [
'port' => 80
],
'timeout_seconds' => 1
]
],
'startup_probe' => [
'enabled' => true,
'probe' => [
'exec' => [
'command' => [
'ls',
'-l'
]
],
'failure_threshold' => 3,
'http_get' => [
'port' => 80,
'headers' => [
'Authorization' => 'Bearer token 123'
],
'host' => '127.0.0.1',
'path' => '/healthz',
'schema' => 'HTTP'
],
'initial_delay_seconds' => 0,
'period_seconds' => 5,
'success_threshold' => 1,
'tcp_socket' => [
'port' => 80
],
'timeout_seconds' => 1
]
]
],
'timeout' => 120
]),
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"
payload := strings.NewReader("{\n \"containers\": [\n {\n \"region_id\": 1,\n \"scale\": {\n \"cooldown_period\": 60,\n \"max\": 3,\n \"min\": 1,\n \"triggers\": {\n \"cpu\": {\n \"threshold\": 80\n },\n \"memory\": {\n \"threshold\": 70\n }\n }\n }\n }\n ],\n \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\",\n \"image\": \"nginx:latest\",\n \"listening_port\": 80,\n \"name\": \"my-instance\",\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"auth_enabled\": false,\n \"command\": [\n \"nginx\",\n \"-g\",\n \"daemon off;\"\n ],\n \"credentials_name\": \"dockerhub\",\n \"description\": \"My first instance\",\n \"envs\": {\n \"DEBUG_MODE\": \"False\",\n \"KEY\": \"12345\"\n },\n \"ingress_opts\": {\n \"disable_response_buffering\": true\n },\n \"logging\": {\n \"destination_region_id\": 1,\n \"enabled\": true,\n \"retention_policy\": {\n \"period\": 42\n },\n \"topic_name\": \"my-log-name\"\n },\n \"probes\": {\n \"liveness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"readiness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"startup_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n }\n },\n \"timeout\": 120\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")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"containers\": [\n {\n \"region_id\": 1,\n \"scale\": {\n \"cooldown_period\": 60,\n \"max\": 3,\n \"min\": 1,\n \"triggers\": {\n \"cpu\": {\n \"threshold\": 80\n },\n \"memory\": {\n \"threshold\": 70\n }\n }\n }\n }\n ],\n \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\",\n \"image\": \"nginx:latest\",\n \"listening_port\": 80,\n \"name\": \"my-instance\",\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"auth_enabled\": false,\n \"command\": [\n \"nginx\",\n \"-g\",\n \"daemon off;\"\n ],\n \"credentials_name\": \"dockerhub\",\n \"description\": \"My first instance\",\n \"envs\": {\n \"DEBUG_MODE\": \"False\",\n \"KEY\": \"12345\"\n },\n \"ingress_opts\": {\n \"disable_response_buffering\": true\n },\n \"logging\": {\n \"destination_region_id\": 1,\n \"enabled\": true,\n \"retention_policy\": {\n \"period\": 42\n },\n \"topic_name\": \"my-log-name\"\n },\n \"probes\": {\n \"liveness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"readiness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"startup_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n }\n },\n \"timeout\": 120\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.gcore.com/cloud/v3/inference/{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 \"containers\": [\n {\n \"region_id\": 1,\n \"scale\": {\n \"cooldown_period\": 60,\n \"max\": 3,\n \"min\": 1,\n \"triggers\": {\n \"cpu\": {\n \"threshold\": 80\n },\n \"memory\": {\n \"threshold\": 70\n }\n }\n }\n }\n ],\n \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\",\n \"image\": \"nginx:latest\",\n \"listening_port\": 80,\n \"name\": \"my-instance\",\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"auth_enabled\": false,\n \"command\": [\n \"nginx\",\n \"-g\",\n \"daemon off;\"\n ],\n \"credentials_name\": \"dockerhub\",\n \"description\": \"My first instance\",\n \"envs\": {\n \"DEBUG_MODE\": \"False\",\n \"KEY\": \"12345\"\n },\n \"ingress_opts\": {\n \"disable_response_buffering\": true\n },\n \"logging\": {\n \"destination_region_id\": 1,\n \"enabled\": true,\n \"retention_policy\": {\n \"period\": 42\n },\n \"topic_name\": \"my-log-name\"\n },\n \"probes\": {\n \"liveness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"readiness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"startup_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n }\n },\n \"timeout\": 120\n}"
response = http.request(request)
puts response.read_body{
"tasks": [
"d478ae29-dedc-4869-82f0-96104425f565"
]
}Everywhere Inference
Create inference deployment
POST
/
cloud
/
v3
/
inference
/
{project_id}
/
deployments
Create inference deployment
curl --request POST \
--url https://api.gcore.com/cloud/v3/inference/{project_id}/deployments \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"containers": [
{
"region_id": 1,
"scale": {
"cooldown_period": 60,
"max": 3,
"min": 1,
"triggers": {
"cpu": {
"threshold": 80
},
"memory": {
"threshold": 70
}
}
}
}
],
"flavor_name": "inference-16vcpu-232gib-1xh100-80gb",
"image": "nginx:latest",
"listening_port": 80,
"name": "my-instance",
"api_keys": [
"key1",
"key2"
],
"auth_enabled": false,
"command": [
"nginx",
"-g",
"daemon off;"
],
"credentials_name": "dockerhub",
"description": "My first instance",
"envs": {
"DEBUG_MODE": "False",
"KEY": "12345"
},
"ingress_opts": {
"disable_response_buffering": true
},
"logging": {
"destination_region_id": 1,
"enabled": true,
"retention_policy": {
"period": 42
},
"topic_name": "my-log-name"
},
"probes": {
"liveness_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
},
"readiness_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
},
"startup_probe": {
"enabled": true,
"probe": {
"exec": {
"command": [
"ls",
"-l"
]
},
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": {
"Authorization": "Bearer token 123"
},
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": {
"port": 80
},
"timeout_seconds": 1
}
}
},
"timeout": 120
}
'import requests
url = "https://api.gcore.com/cloud/v3/inference/{project_id}/deployments"
payload = {
"containers": [
{
"region_id": 1,
"scale": {
"cooldown_period": 60,
"max": 3,
"min": 1,
"triggers": {
"cpu": { "threshold": 80 },
"memory": { "threshold": 70 }
}
}
}
],
"flavor_name": "inference-16vcpu-232gib-1xh100-80gb",
"image": "nginx:latest",
"listening_port": 80,
"name": "my-instance",
"api_keys": ["key1", "key2"],
"auth_enabled": False,
"command": ["nginx", "-g", "daemon off;"],
"credentials_name": "dockerhub",
"description": "My first instance",
"envs": {
"DEBUG_MODE": "False",
"KEY": "12345"
},
"ingress_opts": { "disable_response_buffering": True },
"logging": {
"destination_region_id": 1,
"enabled": True,
"retention_policy": { "period": 42 },
"topic_name": "my-log-name"
},
"probes": {
"liveness_probe": {
"enabled": True,
"probe": {
"exec": { "command": ["ls", "-l"] },
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": { "Authorization": "Bearer token 123" },
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": { "port": 80 },
"timeout_seconds": 1
}
},
"readiness_probe": {
"enabled": True,
"probe": {
"exec": { "command": ["ls", "-l"] },
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": { "Authorization": "Bearer token 123" },
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": { "port": 80 },
"timeout_seconds": 1
}
},
"startup_probe": {
"enabled": True,
"probe": {
"exec": { "command": ["ls", "-l"] },
"failure_threshold": 3,
"http_get": {
"port": 80,
"headers": { "Authorization": "Bearer token 123" },
"host": "127.0.0.1",
"path": "/healthz",
"schema": "HTTP"
},
"initial_delay_seconds": 0,
"period_seconds": 5,
"success_threshold": 1,
"tcp_socket": { "port": 80 },
"timeout_seconds": 1
}
}
},
"timeout": 120
}
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: {
cooldown_period: 60,
max: 3,
min: 1,
triggers: {cpu: {threshold: 80}, memory: {threshold: 70}}
}
}
],
flavor_name: 'inference-16vcpu-232gib-1xh100-80gb',
image: 'nginx:latest',
listening_port: 80,
name: 'my-instance',
api_keys: ['key1', 'key2'],
auth_enabled: false,
command: ['nginx', '-g', 'daemon off;'],
credentials_name: 'dockerhub',
description: 'My first instance',
envs: {DEBUG_MODE: 'False', KEY: '12345'},
ingress_opts: {disable_response_buffering: true},
logging: {
destination_region_id: 1,
enabled: true,
retention_policy: {period: 42},
topic_name: 'my-log-name'
},
probes: {
liveness_probe: {
enabled: true,
probe: {
exec: {command: ['ls', '-l']},
failure_threshold: 3,
http_get: {
port: 80,
headers: {Authorization: 'Bearer token 123'},
host: '127.0.0.1',
path: '/healthz',
schema: 'HTTP'
},
initial_delay_seconds: 0,
period_seconds: 5,
success_threshold: 1,
tcp_socket: {port: 80},
timeout_seconds: 1
}
},
readiness_probe: {
enabled: true,
probe: {
exec: {command: ['ls', '-l']},
failure_threshold: 3,
http_get: {
port: 80,
headers: {Authorization: 'Bearer token 123'},
host: '127.0.0.1',
path: '/healthz',
schema: 'HTTP'
},
initial_delay_seconds: 0,
period_seconds: 5,
success_threshold: 1,
tcp_socket: {port: 80},
timeout_seconds: 1
}
},
startup_probe: {
enabled: true,
probe: {
exec: {command: ['ls', '-l']},
failure_threshold: 3,
http_get: {
port: 80,
headers: {Authorization: 'Bearer token 123'},
host: '127.0.0.1',
path: '/healthz',
schema: 'HTTP'
},
initial_delay_seconds: 0,
period_seconds: 5,
success_threshold: 1,
tcp_socket: {port: 80},
timeout_seconds: 1
}
}
},
timeout: 120
})
};
fetch('https://api.gcore.com/cloud/v3/inference/{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/{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([
'containers' => [
[
'region_id' => 1,
'scale' => [
'cooldown_period' => 60,
'max' => 3,
'min' => 1,
'triggers' => [
'cpu' => [
'threshold' => 80
],
'memory' => [
'threshold' => 70
]
]
]
]
],
'flavor_name' => 'inference-16vcpu-232gib-1xh100-80gb',
'image' => 'nginx:latest',
'listening_port' => 80,
'name' => 'my-instance',
'api_keys' => [
'key1',
'key2'
],
'auth_enabled' => false,
'command' => [
'nginx',
'-g',
'daemon off;'
],
'credentials_name' => 'dockerhub',
'description' => 'My first instance',
'envs' => [
'DEBUG_MODE' => 'False',
'KEY' => '12345'
],
'ingress_opts' => [
'disable_response_buffering' => true
],
'logging' => [
'destination_region_id' => 1,
'enabled' => true,
'retention_policy' => [
'period' => 42
],
'topic_name' => 'my-log-name'
],
'probes' => [
'liveness_probe' => [
'enabled' => true,
'probe' => [
'exec' => [
'command' => [
'ls',
'-l'
]
],
'failure_threshold' => 3,
'http_get' => [
'port' => 80,
'headers' => [
'Authorization' => 'Bearer token 123'
],
'host' => '127.0.0.1',
'path' => '/healthz',
'schema' => 'HTTP'
],
'initial_delay_seconds' => 0,
'period_seconds' => 5,
'success_threshold' => 1,
'tcp_socket' => [
'port' => 80
],
'timeout_seconds' => 1
]
],
'readiness_probe' => [
'enabled' => true,
'probe' => [
'exec' => [
'command' => [
'ls',
'-l'
]
],
'failure_threshold' => 3,
'http_get' => [
'port' => 80,
'headers' => [
'Authorization' => 'Bearer token 123'
],
'host' => '127.0.0.1',
'path' => '/healthz',
'schema' => 'HTTP'
],
'initial_delay_seconds' => 0,
'period_seconds' => 5,
'success_threshold' => 1,
'tcp_socket' => [
'port' => 80
],
'timeout_seconds' => 1
]
],
'startup_probe' => [
'enabled' => true,
'probe' => [
'exec' => [
'command' => [
'ls',
'-l'
]
],
'failure_threshold' => 3,
'http_get' => [
'port' => 80,
'headers' => [
'Authorization' => 'Bearer token 123'
],
'host' => '127.0.0.1',
'path' => '/healthz',
'schema' => 'HTTP'
],
'initial_delay_seconds' => 0,
'period_seconds' => 5,
'success_threshold' => 1,
'tcp_socket' => [
'port' => 80
],
'timeout_seconds' => 1
]
]
],
'timeout' => 120
]),
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"
payload := strings.NewReader("{\n \"containers\": [\n {\n \"region_id\": 1,\n \"scale\": {\n \"cooldown_period\": 60,\n \"max\": 3,\n \"min\": 1,\n \"triggers\": {\n \"cpu\": {\n \"threshold\": 80\n },\n \"memory\": {\n \"threshold\": 70\n }\n }\n }\n }\n ],\n \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\",\n \"image\": \"nginx:latest\",\n \"listening_port\": 80,\n \"name\": \"my-instance\",\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"auth_enabled\": false,\n \"command\": [\n \"nginx\",\n \"-g\",\n \"daemon off;\"\n ],\n \"credentials_name\": \"dockerhub\",\n \"description\": \"My first instance\",\n \"envs\": {\n \"DEBUG_MODE\": \"False\",\n \"KEY\": \"12345\"\n },\n \"ingress_opts\": {\n \"disable_response_buffering\": true\n },\n \"logging\": {\n \"destination_region_id\": 1,\n \"enabled\": true,\n \"retention_policy\": {\n \"period\": 42\n },\n \"topic_name\": \"my-log-name\"\n },\n \"probes\": {\n \"liveness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"readiness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"startup_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n }\n },\n \"timeout\": 120\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")
.header("Authorization", "<api-key>")
.header("Content-Type", "application/json")
.body("{\n \"containers\": [\n {\n \"region_id\": 1,\n \"scale\": {\n \"cooldown_period\": 60,\n \"max\": 3,\n \"min\": 1,\n \"triggers\": {\n \"cpu\": {\n \"threshold\": 80\n },\n \"memory\": {\n \"threshold\": 70\n }\n }\n }\n }\n ],\n \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\",\n \"image\": \"nginx:latest\",\n \"listening_port\": 80,\n \"name\": \"my-instance\",\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"auth_enabled\": false,\n \"command\": [\n \"nginx\",\n \"-g\",\n \"daemon off;\"\n ],\n \"credentials_name\": \"dockerhub\",\n \"description\": \"My first instance\",\n \"envs\": {\n \"DEBUG_MODE\": \"False\",\n \"KEY\": \"12345\"\n },\n \"ingress_opts\": {\n \"disable_response_buffering\": true\n },\n \"logging\": {\n \"destination_region_id\": 1,\n \"enabled\": true,\n \"retention_policy\": {\n \"period\": 42\n },\n \"topic_name\": \"my-log-name\"\n },\n \"probes\": {\n \"liveness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"readiness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"startup_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n }\n },\n \"timeout\": 120\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.gcore.com/cloud/v3/inference/{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 \"containers\": [\n {\n \"region_id\": 1,\n \"scale\": {\n \"cooldown_period\": 60,\n \"max\": 3,\n \"min\": 1,\n \"triggers\": {\n \"cpu\": {\n \"threshold\": 80\n },\n \"memory\": {\n \"threshold\": 70\n }\n }\n }\n }\n ],\n \"flavor_name\": \"inference-16vcpu-232gib-1xh100-80gb\",\n \"image\": \"nginx:latest\",\n \"listening_port\": 80,\n \"name\": \"my-instance\",\n \"api_keys\": [\n \"key1\",\n \"key2\"\n ],\n \"auth_enabled\": false,\n \"command\": [\n \"nginx\",\n \"-g\",\n \"daemon off;\"\n ],\n \"credentials_name\": \"dockerhub\",\n \"description\": \"My first instance\",\n \"envs\": {\n \"DEBUG_MODE\": \"False\",\n \"KEY\": \"12345\"\n },\n \"ingress_opts\": {\n \"disable_response_buffering\": true\n },\n \"logging\": {\n \"destination_region_id\": 1,\n \"enabled\": true,\n \"retention_policy\": {\n \"period\": 42\n },\n \"topic_name\": \"my-log-name\"\n },\n \"probes\": {\n \"liveness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"readiness_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n },\n \"startup_probe\": {\n \"enabled\": true,\n \"probe\": {\n \"exec\": {\n \"command\": [\n \"ls\",\n \"-l\"\n ]\n },\n \"failure_threshold\": 3,\n \"http_get\": {\n \"port\": 80,\n \"headers\": {\n \"Authorization\": \"Bearer token 123\"\n },\n \"host\": \"127.0.0.1\",\n \"path\": \"/healthz\",\n \"schema\": \"HTTP\"\n },\n \"initial_delay_seconds\": 0,\n \"period_seconds\": 5,\n \"success_threshold\": 1,\n \"tcp_socket\": {\n \"port\": 80\n },\n \"timeout_seconds\": 1\n }\n }\n },\n \"timeout\": 120\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
Body
application/json
List of containers for the inference instance.
Minimum array length:
1Show child attributes
Show child attributes
Example:
[
{
"region_id": 1,
"scale": {
"cooldown_period": 60,
"max": 3,
"min": 1,
"triggers": {
"cpu": { "threshold": 80 },
"memory": { "threshold": 70 }
}
}
}
]
Flavor name for the inference instance.
Minimum string length:
1Example:
"inference-16vcpu-232gib-1xh100-80gb"
Docker image for the inference instance. This field should contain the image name and tag in the format 'name:tag', e.g., 'nginx:latest'. It defaults to Docker Hub as the image registry, but any accessible Docker image URL can be specified.
Pattern:
^(?:(?:[a-z0-9]+(?:[._-][a-z0-9]+)*/)*[a-z0-9]+(?:[._-][a-z0-9]+)*)(?::[A-Za-z0-9_][A-Za-z0-9_.-]{0,127})?$Example:
"nginx:latest"
Listening port for the inference instance.
Required range:
1 <= x <= 65535Example:
80
Inference instance name.
Required string length:
4 - 30Pattern:
^[a-z0-9]([-a-z0-9]*[a-z0-9])?$Example:
"my-instance"
List of API keys for the inference instance. Multiple keys can be attached to one deployment.If auth_enabled and api_keys are both specified, a ValidationError will be raised.
Example:
["key1", "key2"]
Set to true to enable API key authentication for the inference instance. "Authorization": "Bearer *****" or "X-Api-Key": "*****" header is required for the requests to the instance if enabled. This field is deprecated and will be removed in the future. Use api_keys field instead.If auth_enabled and api_keys are both specified, a ValidationError will be raised.
Example:
false
Command to be executed when running a container from an image.
Example:
["nginx", "-g", "daemon off;"]
Registry credentials name
Example:
"dockerhub"
Inference instance description.
Example:
"My first instance"
Environment variables for the inference instance.
Show child attributes
Show child attributes
Example:
{ "DEBUG_MODE": "False", "KEY": "12345" }
Ingress options for the inference instance
Show child attributes
Show child attributes
Example:
{ "disable_response_buffering": true }
Logging configuration for the inference instance
Show child attributes
Show child attributes
Example:
{
"destination_region_id": 1,
"enabled": true,
"retention_policy": { "period": 42 },
"topic_name": "my-log-name"
}
Probes configured for all containers of the inference instance. If probes are not provided, and the image_name is from a the Model Catalog registry, the default probes will be used.
Show child attributes
Show child attributes
Specifies the duration in seconds without any requests after which the containers will be downscaled to their minimum scale value as defined by scale.min. If set, this helps in optimizing resource usage by reducing the number of container instances during periods of inactivity. The default value when the parameter is not set is 120.
Required range:
x >= 0Example:
120
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