Skip to main content
PUT
/
api
/
v0
/
endptjobs
/
{id}
update endpoint
curl --request PUT \
  --url https://console.vast.ai/api/v0/endptjobs/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "min_load": 0,
  "target_util": 0.9,
  "cold_mult": 2.5,
  "cold_workers": 5,
  "max_workers": 20,
  "endpoint_name": "my_endpoint"
}
'
import requests

url = "https://console.vast.ai/api/v0/endptjobs/{id}"

payload = {
"min_load": 0,
"target_util": 0.9,
"cold_mult": 2.5,
"cold_workers": 5,
"max_workers": 20,
"endpoint_name": "my_endpoint"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}

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

print(response.text)
const options = {
method: 'PUT',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({
min_load: 0,
target_util: 0.9,
cold_mult: 2.5,
cold_workers: 5,
max_workers: 20,
endpoint_name: 'my_endpoint'
})
};

fetch('https://console.vast.ai/api/v0/endptjobs/{id}', 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://console.vast.ai/api/v0/endptjobs/{id}",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "PUT",
CURLOPT_POSTFIELDS => json_encode([
'min_load' => 0,
'target_util' => 0.9,
'cold_mult' => 2.5,
'cold_workers' => 5,
'max_workers' => 20,
'endpoint_name' => 'my_endpoint'
]),
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"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://console.vast.ai/api/v0/endptjobs/{id}"

payload := strings.NewReader("{\n \"min_load\": 0,\n \"target_util\": 0.9,\n \"cold_mult\": 2.5,\n \"cold_workers\": 5,\n \"max_workers\": 20,\n \"endpoint_name\": \"my_endpoint\"\n}")

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

req.Header.Add("Authorization", "Bearer <token>")
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.put("https://console.vast.ai/api/v0/endptjobs/{id}")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"min_load\": 0,\n \"target_util\": 0.9,\n \"cold_mult\": 2.5,\n \"cold_workers\": 5,\n \"max_workers\": 20,\n \"endpoint_name\": \"my_endpoint\"\n}")
.asString();
require 'uri'
require 'net/http'

url = URI("https://console.vast.ai/api/v0/endptjobs/{id}")

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

request = Net::HTTP::Put.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n \"min_load\": 0,\n \"target_util\": 0.9,\n \"cold_mult\": 2.5,\n \"cold_workers\": 5,\n \"max_workers\": 20,\n \"endpoint_name\": \"my_endpoint\"\n}"

response = http.request(request)
puts response.read_body
{
  "success": true
}
{
"success": false,
"error": "invalid_args",
"msg": "Endpointgroup not found for user"
}
{
"success": false,
"error": "<string>",
"msg": "<string>"
}
{
"detail": "API requests too frequent endpoint threshold=2.0"
}

Authorizations

Authorization
string
header
required

API key must be provided in the Authorization header

Path Parameters

id
integer
required

ID of the endpoint group to update

Example:

4242

Body

application/json
min_load
number

Minimum floor load in perf units/s (token/s for LLMs)

Example:

0

target_util
number

Target capacity utilization (fraction, max 1.0)

Example:

0.9

cold_mult
number

Cold/stopped instance capacity target as multiple of hot capacity target

Example:

2.5

cold_workers
integer

Min number of workers to keep 'cold' when you have no load

Example:

5

max_workers
integer

Max number of workers your endpoint group can have

Example:

20

endpoint_name
string

Deployment endpoint name

Example:

"my_endpoint"

Response

Success response

success
boolean
Example:

true