Update Endpoint

Updates autoscaling configuration on an existing endpoint; endpoint must not be managed by a deployment.

PUT /api/v0/endptjobs/{id}/

Update Endpoint

cURL

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,
  "min_cold_load": 0.05,
  "target_util": 0.9,
  "cold_mult": 2.5,
  "cold_workers": 5,
  "max_workers": 20,
  "max_queue_time": 90,
  "target_queue_time": 15,
  "endpoint_name": "my_endpoint",
  "autoscaler_instance": "prod",
  "endpoint_state": "active",
  "inactivity_timeout": 600,
  "overrecruit_ratio": 1.3
}
'

import requests

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

payload = {
    "min_load": 0,
    "min_cold_load": 0.05,
    "target_util": 0.9,
    "cold_mult": 2.5,
    "cold_workers": 5,
    "max_workers": 20,
    "max_queue_time": 90,
    "target_queue_time": 15,
    "endpoint_name": "my_endpoint",
    "autoscaler_instance": "prod",
    "endpoint_state": "active",
    "inactivity_timeout": 600,
    "overrecruit_ratio": 1.3
}
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,
    min_cold_load: 0.05,
    target_util: 0.9,
    cold_mult: 2.5,
    cold_workers: 5,
    max_workers: 20,
    max_queue_time: 90,
    target_queue_time: 15,
    endpoint_name: 'my_endpoint',
    autoscaler_instance: 'prod',
    endpoint_state: 'active',
    inactivity_timeout: 600,
    overrecruit_ratio: 1.3
  })
};

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,
    'min_cold_load' => 0.05,
    'target_util' => 0.9,
    'cold_mult' => 2.5,
    'cold_workers' => 5,
    'max_workers' => 20,
    'max_queue_time' => 90,
    'target_queue_time' => 15,
    'endpoint_name' => 'my_endpoint',
    'autoscaler_instance' => 'prod',
    'endpoint_state' => 'active',
    'inactivity_timeout' => 600,
    'overrecruit_ratio' => 1.3
  ]),
  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  \"min_cold_load\": 0.05,\n  \"target_util\": 0.9,\n  \"cold_mult\": 2.5,\n  \"cold_workers\": 5,\n  \"max_workers\": 20,\n  \"max_queue_time\": 90,\n  \"target_queue_time\": 15,\n  \"endpoint_name\": \"my_endpoint\",\n  \"autoscaler_instance\": \"prod\",\n  \"endpoint_state\": \"active\",\n  \"inactivity_timeout\": 600,\n  \"overrecruit_ratio\": 1.3\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  \"min_cold_load\": 0.05,\n  \"target_util\": 0.9,\n  \"cold_mult\": 2.5,\n  \"cold_workers\": 5,\n  \"max_workers\": 20,\n  \"max_queue_time\": 90,\n  \"target_queue_time\": 15,\n  \"endpoint_name\": \"my_endpoint\",\n  \"autoscaler_instance\": \"prod\",\n  \"endpoint_state\": \"active\",\n  \"inactivity_timeout\": 600,\n  \"overrecruit_ratio\": 1.3\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  \"min_cold_load\": 0.05,\n  \"target_util\": 0.9,\n  \"cold_mult\": 2.5,\n  \"cold_workers\": 5,\n  \"max_workers\": 20,\n  \"max_queue_time\": 90,\n  \"target_queue_time\": 15,\n  \"endpoint_name\": \"my_endpoint\",\n  \"autoscaler_instance\": \"prod\",\n  \"endpoint_state\": \"active\",\n  \"inactivity_timeout\": 600,\n  \"overrecruit_ratio\": 1.3\n}"

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

200

{
  "success": true
}

{
  "error": "<string>",
  "msg": "<string>"
}

{
  "error": "<string>",
  "msg": "<string>"
}

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

Body

application/json

min_load · number

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

Example:

0

min_cold_load · number

Updated minimum cold load threshold.

Example:

0.05

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

max_queue_time · number

Updated maximum acceptable queue time in seconds.

Example:

90

target_queue_time · number

Updated desired queue time in seconds; must be <= max_queue_time.

Example:

15

endpoint_name · string

Deployment endpoint name

Example:

"my_endpoint"

autoscaler_instance · string

Autoscaler deployment environment.

Example:

"prod"

endpoint_state · enum<string>

New activation state for the endpoint.

Available options: active, suspended, stopped

Example:

"active"

inactivity_timeout · number

Updated seconds of inactivity before suspension.

Example:

600

overrecruit_ratio · number

Updated over-recruit ratio for traffic spike absorption.

Example:

1.3

Response

200

application/json

Returns {success: true}

success · boolean

Always true on success.