curl --request POST \
--url https://api.novita.ai/gpus/v2/endpoints \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"type": "sync",
"name": "example-endpoint",
"product_id": "product-id",
"image": "registry.example.com/namespace/image:tag",
"worker_config": {
"max_replicas": 2,
"min_replicas": 0,
"idle_timeout": 300,
"max_concurrent_per_worker": 10,
"gpu_num": 1,
"rootfs_size_gb": 20,
"min_cuda_version": "12.4",
"request_timeout": 60
},
"app_name": "example-app",
"registry_auth_id": "registry-auth-id",
"entrypoint": "",
"command": "",
"policy": {
"type": "queue",
"value": 100
},
"volumes": [
{
"id": "storage-id",
"type": "network",
"size": 123,
"mount_point": "/data"
}
],
"envs": [
{
"key": "ENV_NAME",
"value": "ENV_VALUE"
}
],
"ports": [
8080
],
"health_check": {
"path": "/healthz",
"port": 8080
},
"region_id": "region-id"
}
'import requests
url = "https://api.novita.ai/gpus/v2/endpoints"
payload = {
"type": "sync",
"name": "example-endpoint",
"product_id": "product-id",
"image": "registry.example.com/namespace/image:tag",
"worker_config": {
"max_replicas": 2,
"min_replicas": 0,
"idle_timeout": 300,
"max_concurrent_per_worker": 10,
"gpu_num": 1,
"rootfs_size_gb": 20,
"min_cuda_version": "12.4",
"request_timeout": 60
},
"app_name": "example-app",
"registry_auth_id": "registry-auth-id",
"entrypoint": "",
"command": "",
"policy": {
"type": "queue",
"value": 100
},
"volumes": [
{
"id": "storage-id",
"type": "network",
"size": 123,
"mount_point": "/data"
}
],
"envs": [
{
"key": "ENV_NAME",
"value": "ENV_VALUE"
}
],
"ports": [8080],
"health_check": {
"path": "/healthz",
"port": 8080
},
"region_id": "region-id"
}
headers = {
"Content-Type": "<content-type>",
"Authorization": "<authorization>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
body: JSON.stringify({
type: 'sync',
name: 'example-endpoint',
product_id: 'product-id',
image: 'registry.example.com/namespace/image:tag',
worker_config: {
max_replicas: 2,
min_replicas: 0,
idle_timeout: 300,
max_concurrent_per_worker: 10,
gpu_num: 1,
rootfs_size_gb: 20,
min_cuda_version: '12.4',
request_timeout: 60
},
app_name: 'example-app',
registry_auth_id: 'registry-auth-id',
entrypoint: '',
command: '',
policy: {type: 'queue', value: 100},
volumes: [{id: 'storage-id', type: 'network', size: 123, mount_point: '/data'}],
envs: [{key: 'ENV_NAME', value: 'ENV_VALUE'}],
ports: [8080],
health_check: {path: '/healthz', port: 8080},
region_id: 'region-id'
})
};
fetch('https://api.novita.ai/gpus/v2/endpoints', 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.novita.ai/gpus/v2/endpoints",
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([
'type' => 'sync',
'name' => 'example-endpoint',
'product_id' => 'product-id',
'image' => 'registry.example.com/namespace/image:tag',
'worker_config' => [
'max_replicas' => 2,
'min_replicas' => 0,
'idle_timeout' => 300,
'max_concurrent_per_worker' => 10,
'gpu_num' => 1,
'rootfs_size_gb' => 20,
'min_cuda_version' => '12.4',
'request_timeout' => 60
],
'app_name' => 'example-app',
'registry_auth_id' => 'registry-auth-id',
'entrypoint' => '',
'command' => '',
'policy' => [
'type' => 'queue',
'value' => 100
],
'volumes' => [
[
'id' => 'storage-id',
'type' => 'network',
'size' => 123,
'mount_point' => '/data'
]
],
'envs' => [
[
'key' => 'ENV_NAME',
'value' => 'ENV_VALUE'
]
],
'ports' => [
8080
],
'health_check' => [
'path' => '/healthz',
'port' => 8080
],
'region_id' => 'region-id'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($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.novita.ai/gpus/v2/endpoints"
payload := strings.NewReader("{\n \"type\": \"sync\",\n \"name\": \"example-endpoint\",\n \"product_id\": \"product-id\",\n \"image\": \"registry.example.com/namespace/image:tag\",\n \"worker_config\": {\n \"max_replicas\": 2,\n \"min_replicas\": 0,\n \"idle_timeout\": 300,\n \"max_concurrent_per_worker\": 10,\n \"gpu_num\": 1,\n \"rootfs_size_gb\": 20,\n \"min_cuda_version\": \"12.4\",\n \"request_timeout\": 60\n },\n \"app_name\": \"example-app\",\n \"registry_auth_id\": \"registry-auth-id\",\n \"entrypoint\": \"\",\n \"command\": \"\",\n \"policy\": {\n \"type\": \"queue\",\n \"value\": 100\n },\n \"volumes\": [\n {\n \"id\": \"storage-id\",\n \"type\": \"network\",\n \"size\": 123,\n \"mount_point\": \"/data\"\n }\n ],\n \"envs\": [\n {\n \"key\": \"ENV_NAME\",\n \"value\": \"ENV_VALUE\"\n }\n ],\n \"ports\": [\n 8080\n ],\n \"health_check\": {\n \"path\": \"/healthz\",\n \"port\": 8080\n },\n \"region_id\": \"region-id\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Content-Type", "<content-type>")
req.Header.Add("Authorization", "<authorization>")
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.novita.ai/gpus/v2/endpoints")
.header("Content-Type", "<content-type>")
.header("Authorization", "<authorization>")
.body("{\n \"type\": \"sync\",\n \"name\": \"example-endpoint\",\n \"product_id\": \"product-id\",\n \"image\": \"registry.example.com/namespace/image:tag\",\n \"worker_config\": {\n \"max_replicas\": 2,\n \"min_replicas\": 0,\n \"idle_timeout\": 300,\n \"max_concurrent_per_worker\": 10,\n \"gpu_num\": 1,\n \"rootfs_size_gb\": 20,\n \"min_cuda_version\": \"12.4\",\n \"request_timeout\": 60\n },\n \"app_name\": \"example-app\",\n \"registry_auth_id\": \"registry-auth-id\",\n \"entrypoint\": \"\",\n \"command\": \"\",\n \"policy\": {\n \"type\": \"queue\",\n \"value\": 100\n },\n \"volumes\": [\n {\n \"id\": \"storage-id\",\n \"type\": \"network\",\n \"size\": 123,\n \"mount_point\": \"/data\"\n }\n ],\n \"envs\": [\n {\n \"key\": \"ENV_NAME\",\n \"value\": \"ENV_VALUE\"\n }\n ],\n \"ports\": [\n 8080\n ],\n \"health_check\": {\n \"path\": \"/healthz\",\n \"port\": 8080\n },\n \"region_id\": \"region-id\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.novita.ai/gpus/v2/endpoints")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n \"type\": \"sync\",\n \"name\": \"example-endpoint\",\n \"product_id\": \"product-id\",\n \"image\": \"registry.example.com/namespace/image:tag\",\n \"worker_config\": {\n \"max_replicas\": 2,\n \"min_replicas\": 0,\n \"idle_timeout\": 300,\n \"max_concurrent_per_worker\": 10,\n \"gpu_num\": 1,\n \"rootfs_size_gb\": 20,\n \"min_cuda_version\": \"12.4\",\n \"request_timeout\": 60\n },\n \"app_name\": \"example-app\",\n \"registry_auth_id\": \"registry-auth-id\",\n \"entrypoint\": \"\",\n \"command\": \"\",\n \"policy\": {\n \"type\": \"queue\",\n \"value\": 100\n },\n \"volumes\": [\n {\n \"id\": \"storage-id\",\n \"type\": \"network\",\n \"size\": 123,\n \"mount_point\": \"/data\"\n }\n ],\n \"envs\": [\n {\n \"key\": \"ENV_NAME\",\n \"value\": \"ENV_VALUE\"\n }\n ],\n \"ports\": [\n 8080\n ],\n \"health_check\": {\n \"path\": \"/healthz\",\n \"port\": 8080\n },\n \"region_id\": \"region-id\"\n}"
response = http.request(request)
puts response.read_body{
"id": "endpoint-id"
}Create Endpoint
curl --request POST \
--url https://api.novita.ai/gpus/v2/endpoints \
--header 'Authorization: <authorization>' \
--header 'Content-Type: <content-type>' \
--data '
{
"type": "sync",
"name": "example-endpoint",
"product_id": "product-id",
"image": "registry.example.com/namespace/image:tag",
"worker_config": {
"max_replicas": 2,
"min_replicas": 0,
"idle_timeout": 300,
"max_concurrent_per_worker": 10,
"gpu_num": 1,
"rootfs_size_gb": 20,
"min_cuda_version": "12.4",
"request_timeout": 60
},
"app_name": "example-app",
"registry_auth_id": "registry-auth-id",
"entrypoint": "",
"command": "",
"policy": {
"type": "queue",
"value": 100
},
"volumes": [
{
"id": "storage-id",
"type": "network",
"size": 123,
"mount_point": "/data"
}
],
"envs": [
{
"key": "ENV_NAME",
"value": "ENV_VALUE"
}
],
"ports": [
8080
],
"health_check": {
"path": "/healthz",
"port": 8080
},
"region_id": "region-id"
}
'import requests
url = "https://api.novita.ai/gpus/v2/endpoints"
payload = {
"type": "sync",
"name": "example-endpoint",
"product_id": "product-id",
"image": "registry.example.com/namespace/image:tag",
"worker_config": {
"max_replicas": 2,
"min_replicas": 0,
"idle_timeout": 300,
"max_concurrent_per_worker": 10,
"gpu_num": 1,
"rootfs_size_gb": 20,
"min_cuda_version": "12.4",
"request_timeout": 60
},
"app_name": "example-app",
"registry_auth_id": "registry-auth-id",
"entrypoint": "",
"command": "",
"policy": {
"type": "queue",
"value": 100
},
"volumes": [
{
"id": "storage-id",
"type": "network",
"size": 123,
"mount_point": "/data"
}
],
"envs": [
{
"key": "ENV_NAME",
"value": "ENV_VALUE"
}
],
"ports": [8080],
"health_check": {
"path": "/healthz",
"port": 8080
},
"region_id": "region-id"
}
headers = {
"Content-Type": "<content-type>",
"Authorization": "<authorization>"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text)const options = {
method: 'POST',
headers: {'Content-Type': '<content-type>', Authorization: '<authorization>'},
body: JSON.stringify({
type: 'sync',
name: 'example-endpoint',
product_id: 'product-id',
image: 'registry.example.com/namespace/image:tag',
worker_config: {
max_replicas: 2,
min_replicas: 0,
idle_timeout: 300,
max_concurrent_per_worker: 10,
gpu_num: 1,
rootfs_size_gb: 20,
min_cuda_version: '12.4',
request_timeout: 60
},
app_name: 'example-app',
registry_auth_id: 'registry-auth-id',
entrypoint: '',
command: '',
policy: {type: 'queue', value: 100},
volumes: [{id: 'storage-id', type: 'network', size: 123, mount_point: '/data'}],
envs: [{key: 'ENV_NAME', value: 'ENV_VALUE'}],
ports: [8080],
health_check: {path: '/healthz', port: 8080},
region_id: 'region-id'
})
};
fetch('https://api.novita.ai/gpus/v2/endpoints', 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.novita.ai/gpus/v2/endpoints",
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([
'type' => 'sync',
'name' => 'example-endpoint',
'product_id' => 'product-id',
'image' => 'registry.example.com/namespace/image:tag',
'worker_config' => [
'max_replicas' => 2,
'min_replicas' => 0,
'idle_timeout' => 300,
'max_concurrent_per_worker' => 10,
'gpu_num' => 1,
'rootfs_size_gb' => 20,
'min_cuda_version' => '12.4',
'request_timeout' => 60
],
'app_name' => 'example-app',
'registry_auth_id' => 'registry-auth-id',
'entrypoint' => '',
'command' => '',
'policy' => [
'type' => 'queue',
'value' => 100
],
'volumes' => [
[
'id' => 'storage-id',
'type' => 'network',
'size' => 123,
'mount_point' => '/data'
]
],
'envs' => [
[
'key' => 'ENV_NAME',
'value' => 'ENV_VALUE'
]
],
'ports' => [
8080
],
'health_check' => [
'path' => '/healthz',
'port' => 8080
],
'region_id' => 'region-id'
]),
CURLOPT_HTTPHEADER => [
"Authorization: <authorization>",
"Content-Type: <content-type>"
],
]);
$response = curl_exec($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.novita.ai/gpus/v2/endpoints"
payload := strings.NewReader("{\n \"type\": \"sync\",\n \"name\": \"example-endpoint\",\n \"product_id\": \"product-id\",\n \"image\": \"registry.example.com/namespace/image:tag\",\n \"worker_config\": {\n \"max_replicas\": 2,\n \"min_replicas\": 0,\n \"idle_timeout\": 300,\n \"max_concurrent_per_worker\": 10,\n \"gpu_num\": 1,\n \"rootfs_size_gb\": 20,\n \"min_cuda_version\": \"12.4\",\n \"request_timeout\": 60\n },\n \"app_name\": \"example-app\",\n \"registry_auth_id\": \"registry-auth-id\",\n \"entrypoint\": \"\",\n \"command\": \"\",\n \"policy\": {\n \"type\": \"queue\",\n \"value\": 100\n },\n \"volumes\": [\n {\n \"id\": \"storage-id\",\n \"type\": \"network\",\n \"size\": 123,\n \"mount_point\": \"/data\"\n }\n ],\n \"envs\": [\n {\n \"key\": \"ENV_NAME\",\n \"value\": \"ENV_VALUE\"\n }\n ],\n \"ports\": [\n 8080\n ],\n \"health_check\": {\n \"path\": \"/healthz\",\n \"port\": 8080\n },\n \"region_id\": \"region-id\"\n}")
req, _ := http.NewRequest("POST", url, payload)
req.Header.Add("Content-Type", "<content-type>")
req.Header.Add("Authorization", "<authorization>")
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.novita.ai/gpus/v2/endpoints")
.header("Content-Type", "<content-type>")
.header("Authorization", "<authorization>")
.body("{\n \"type\": \"sync\",\n \"name\": \"example-endpoint\",\n \"product_id\": \"product-id\",\n \"image\": \"registry.example.com/namespace/image:tag\",\n \"worker_config\": {\n \"max_replicas\": 2,\n \"min_replicas\": 0,\n \"idle_timeout\": 300,\n \"max_concurrent_per_worker\": 10,\n \"gpu_num\": 1,\n \"rootfs_size_gb\": 20,\n \"min_cuda_version\": \"12.4\",\n \"request_timeout\": 60\n },\n \"app_name\": \"example-app\",\n \"registry_auth_id\": \"registry-auth-id\",\n \"entrypoint\": \"\",\n \"command\": \"\",\n \"policy\": {\n \"type\": \"queue\",\n \"value\": 100\n },\n \"volumes\": [\n {\n \"id\": \"storage-id\",\n \"type\": \"network\",\n \"size\": 123,\n \"mount_point\": \"/data\"\n }\n ],\n \"envs\": [\n {\n \"key\": \"ENV_NAME\",\n \"value\": \"ENV_VALUE\"\n }\n ],\n \"ports\": [\n 8080\n ],\n \"health_check\": {\n \"path\": \"/healthz\",\n \"port\": 8080\n },\n \"region_id\": \"region-id\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.novita.ai/gpus/v2/endpoints")
http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true
request = Net::HTTP::Post.new(url)
request["Content-Type"] = '<content-type>'
request["Authorization"] = '<authorization>'
request.body = "{\n \"type\": \"sync\",\n \"name\": \"example-endpoint\",\n \"product_id\": \"product-id\",\n \"image\": \"registry.example.com/namespace/image:tag\",\n \"worker_config\": {\n \"max_replicas\": 2,\n \"min_replicas\": 0,\n \"idle_timeout\": 300,\n \"max_concurrent_per_worker\": 10,\n \"gpu_num\": 1,\n \"rootfs_size_gb\": 20,\n \"min_cuda_version\": \"12.4\",\n \"request_timeout\": 60\n },\n \"app_name\": \"example-app\",\n \"registry_auth_id\": \"registry-auth-id\",\n \"entrypoint\": \"\",\n \"command\": \"\",\n \"policy\": {\n \"type\": \"queue\",\n \"value\": 100\n },\n \"volumes\": [\n {\n \"id\": \"storage-id\",\n \"type\": \"network\",\n \"size\": 123,\n \"mount_point\": \"/data\"\n }\n ],\n \"envs\": [\n {\n \"key\": \"ENV_NAME\",\n \"value\": \"ENV_VALUE\"\n }\n ],\n \"ports\": [\n 8080\n ],\n \"health_check\": {\n \"path\": \"/healthz\",\n \"port\": 8080\n },\n \"region_id\": \"region-id\"\n}"
response = http.request(request)
puts response.read_body{
"id": "endpoint-id"
}Headers
Allowed value: application/json.
Bearer authentication format, e.g.: Bearer {{API_KEY}}.
Body
Endpoint type. Allowed values: sync, async.
sync, async "sync"
Endpoint name. String, length: 1-255 characters.
"example-endpoint"
Serverless product ID. String, length: 1-255 characters.
"product-id"
Image address. String, length: 1-500 characters.
"registry.example.com/namespace/image:tag"
Worker configuration.
Show child attributes
Show child attributes
Application name. String, length: 0-255 characters.
"example-app"
Saved registry authentication ID. String, length: 0-255 characters.
"registry-auth-id"
Container entrypoint.
""
Startup command.
""
Scheduling / request policy.
Show child attributes
Show child attributes
Mount list.
Show child attributes
Show child attributes
Environment variable list.
Show child attributes
Show child attributes
Port list. Each value in range: [1, 65535].
[8080]Health check configuration.
Show child attributes
Show child attributes
Region ID.
"region-id"
Response
OK
ID of the created Endpoint
"endpoint-id"
Was this page helpful?