Serverless

Update a serverless endpoint

Partially updates a serverless endpoint. This is a PATCH: only the fields present in the body are changed; omitted fields are left untouched. See UpdateEndpointRequest for the full body.

Mutable fields: name, gpu, cpu, workers (min/max), scaling (type/value/idleTimeout), dataCenterIds, networkVolumes, timeout, flashboot, and the container settings (image, args, disk, ports, env, registry).

Omitted compute preserves the current selection. cpu completely replaces a CPU endpoint’s selection; compute family is immutable. gpu on CPU, cpu on GPU, or both fields returns 400.

Returns 200 with the full updated endpoint. Effect timing differs by field: scaling and worker-bound settings (workers, scaling, timeout) are applied to the autoscaler promptly, while container-affecting changes (e.g. image, env) create a new endpoint release that rolls out as workers cycle — in-flight workers keep the previous version until they are replaced. Track rollout via listEndpointReleases.

PATCH

serverless

{id}

Update a serverless endpoint

curl --request PATCH \
  --url https://api.runpod.io/v2/serverless/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "workers": {
    "min": 1,
    "max": 10,
    "idleTimeout": 10
  },
  "scaling": {
    "type": "QUEUE_DELAY",
    "queueDelay": 8
  }
}
'

import requests

url = "https://api.runpod.io/v2/serverless/{id}"

payload = {
    "workers": {
        "min": 1,
        "max": 10,
        "idleTimeout": 10
    },
    "scaling": {
        "type": "QUEUE_DELAY",
        "queueDelay": 8
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    workers: {min: 1, max: 10, idleTimeout: 10},
    scaling: {type: 'QUEUE_DELAY', queueDelay: 8}
  })
};

fetch('https://api.runpod.io/v2/serverless/{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://api.runpod.io/v2/serverless/{id}",
  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([
    'workers' => [
        'min' => 1,
        'max' => 10,
        'idleTimeout' => 10
    ],
    'scaling' => [
        'type' => 'QUEUE_DELAY',
        'queueDelay' => 8
    ]
  ]),
  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://api.runpod.io/v2/serverless/{id}"

	payload := strings.NewReader("{\n  \"workers\": {\n    \"min\": 1,\n    \"max\": 10,\n    \"idleTimeout\": 10\n  },\n  \"scaling\": {\n    \"type\": \"QUEUE_DELAY\",\n    \"queueDelay\": 8\n  }\n}")

	req, _ := http.NewRequest("PATCH", 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.patch("https://api.runpod.io/v2/serverless/{id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"workers\": {\n    \"min\": 1,\n    \"max\": 10,\n    \"idleTimeout\": 10\n  },\n  \"scaling\": {\n    \"type\": \"QUEUE_DELAY\",\n    \"queueDelay\": 8\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.runpod.io/v2/serverless/{id}")

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

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"workers\": {\n    \"min\": 1,\n    \"max\": 10,\n    \"idleTimeout\": 10\n  },\n  \"scaling\": {\n    \"type\": \"QUEUE_DELAY\",\n    \"queueDelay\": 8\n  }\n}"

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

{
  "id": "4m7x2k9q",
  "name": "image-generator",
  "type": "QUEUE",
  "requestUrls": {
    "run": "https://api.runpod.ai/v2/4m7x2k9q/run",
    "runSync": "https://api.runpod.ai/v2/4m7x2k9q/runsync",
    "status": "https://api.runpod.ai/v2/4m7x2k9q/status/{job_id}",
    "stream": "https://api.runpod.ai/v2/4m7x2k9q/stream/{job_id}",
    "cancel": "https://api.runpod.ai/v2/4m7x2k9q/cancel/{job_id}",
    "retry": "https://api.runpod.ai/v2/4m7x2k9q/retry/{job_id}",
    "purgeQueue": "https://api.runpod.ai/v2/4m7x2k9q/purge-queue",
    "health": "https://api.runpod.ai/v2/4m7x2k9q/health"
  },
  "image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
  "args": "",
  "disk": 20,
  "ports": [
    "8000/http"
  ],
  "env": {
    "MODEL_NAME": "sdxl"
  },
  "registry": null,
  "gpu": {
    "pools": [
      "ADA_24"
    ],
    "count": 1,
    "allowedCudaVersions": [],
    "minCudaVersion": null
  },
  "workers": {
    "min": 1,
    "max": 10,
    "idleTimeout": 10
  },
  "scaling": {
    "type": "QUEUE_DELAY",
    "queueDelay": 8
  },
  "dataCenterIds": [
    "US-KS-2"
  ],
  "networkVolumes": [
    "2q9m7x4c"
  ],
  "timeout": 300000,
  "flashboot": "OFF",
  "createdAt": "2026-06-01T12:00:00Z"
}

{
  "title": "Bad Request",
  "status": 400,
  "detail": "request could not be processed"
}

{
  "title": "Unauthorized",
  "status": 401,
  "detail": "missing bearer token"
}

{
  "title": "Forbidden",
  "status": 403,
  "detail": "access denied"
}

{
  "title": "Not Found",
  "status": 404,
  "detail": "resource not found"
}

{
  "title": "Unprocessable Entity",
  "status": 422,
  "detail": "Request validation failed."
}

{
  "title": "Too Many Requests",
  "status": 429,
  "detail": "rate limit exceeded for the minute window"
}

{
  "title": "<string>",
  "status": 123,
  "detail": "<string>",
  "errors": [
    "<string>"
  ]
}

Authorizations

Authorization

string

header

required

Runpod API key authentication. Generate an API key in the Runpod console and send it in the Authorization header as Bearer <api_key>. Keys are scoped to the permissions granted when created; requests may return 403 when a valid key lacks access to the requested resource or action.

Path Parameters

string

required

Serverless endpoint identifier

Body

application/json

Only provided fields are changed.

args

string

Arguments passed to the container entrypoint

Example:

""

disk

integer

Container disk in GB (ephemeral, wiped on restart)

Required range: x >= 1

Example:

50

env

object

Environment variables as key-value pairs

Show child attributes

Example:

{ "JUPYTER_PASSWORD": "hunter2" }

image

string

Docker image reference

Example:

"runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404"

ports

string[]

Exposed ports, formatted as port/protocol

Example:

["8888/http", "22/tcp"]

registry

string | null

Container registry credential ID (for private images)

Example:

null

cpu

object[]

Complete replacement CPU selection. Valid only for an existing CPU endpoint; endpoint compute family cannot be changed.

Minimum array length: 1

Show child attributes

dataCenterIds

string[]

Preferred data centers for placement. Omit or pass an empty array to let the scheduler choose.

flashboot

enum<string>

FlashBoot cold-start acceleration mode.

OFF — disabled
FLASHBOOT — enabled
PRIORITY_FLASHBOOT — enabled with priority capacity

Available options:

OFF,

FLASHBOOT,

PRIORITY_FLASHBOOT

gpu

object

Partial GPU update — every field is optional and an omitted one is left unchanged. Unlike create, pools is optional, so changing only a CUDA constraint does not require resending the pool list.

excludedTypes requires pools, because the two are one selection and only a supplied pools replaces it — an exclusion on its own would otherwise be silently dropped.

Show child attributes

name

string

Minimum string length: 1

networkVolumes

string[]

scaling

object

Autoscaling signal — a discriminated union on type: QUEUE_DELAY (queue-based endpoints only) or REQUEST_COUNT. The scaler is chosen independently of the endpoint's routing type and can be switched on update.

Option 1
Option 2

Show child attributes

templateId

string

ID of a serverless template whose container settings are applied as if they were provided in this PATCH body (image, args, disk, ports, env, registry). Explicit body fields override the template's; env merges template and body per key (body wins) and, per PATCH semantics, replaces the endpoint's env. One-time application — no link to the template is retained. Must be one of your templates or a public template (unknown or inaccessible ID → 404); must be a serverless template (→ 422).

Example:

"30zmvf89kd"

timeout

integer

workers

object

Show child attributes

Response

Reusable container configuration shared across templates, pods, and serverless endpoints. Adding a field here automatically propagates to all three resources.

string

required

Example:

"ep_abc123"

name

string

required

Example:

"my-inference"

workers

object

required

Show child attributes

scaling

object

required

Option 1
Option 2

Show child attributes

dataCenterIds

string[]

required

Example:

["US-TX-3"]

networkVolumes

string[]

required

Example:

["vol_abc"]

timeout

integer

required

Per-request execution timeout in milliseconds

Example:

300000

flashboot

enum<string>

required

FlashBoot cold-start acceleration mode.

OFF — disabled
FLASHBOOT — enabled
PRIORITY_FLASHBOOT — enabled with priority capacity

Available options:

OFF,

FLASHBOOT,

PRIORITY_FLASHBOOT

createdAt

string<date-time>

required

Example:

"2026-03-13T20:00:00Z"

args

string

Arguments passed to the container entrypoint

Example:

""

disk

integer

Container disk in GB (ephemeral, wiped on restart)

Required range: x >= 1

Example:

50

env

object

Environment variables as key-value pairs

Show child attributes

Example:

{ "JUPYTER_PASSWORD": "hunter2" }

image

string

Docker image reference

Example:

"runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404"

ports

string[]

Exposed ports, formatted as port/protocol

Example:

["8888/http", "22/tcp"]

registry

string | null

Container registry credential ID (for private images)

Example:

null

type

enum<string>

Request-routing semantics for a modern serverless endpoint.

QUEUE — submit asynchronous or synchronous jobs through the managed queue.
LOAD_BALANCER — send requests directly to worker-defined HTTP paths. Configure via env: PORT (server port, default 80), PORT_HEALTH (health-check port, default 80), and HEALTH_CHECK_PATH (path the load balancer polls for worker health, default /ping).

Available options:

QUEUE,

LOAD_BALANCER

requestUrls

object

Request URLs appropriate to the endpoint's top-level type. Queue-based endpoints provide job submission and management URLs; load-balancing endpoints provide base and health because their remaining paths are worker-defined.

Option 1
Option 2

Show child attributes

gpu

object | null

Show child attributes

cpu

object[]

Eligible CPU configurations for each worker, in the order they were submitted. Present for CPU endpoints and omitted for GPU endpoints. Memory is derived from the selected flavor's catalog RAM multiplier.

Minimum array length: 1

Show child attributes

Last modified on July 28, 2026

⌘I

Update a serverless endpoint

curl --request PATCH \
  --url https://api.runpod.io/v2/serverless/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "workers": {
    "min": 1,
    "max": 10,
    "idleTimeout": 10
  },
  "scaling": {
    "type": "QUEUE_DELAY",
    "queueDelay": 8
  }
}
'

import requests

url = "https://api.runpod.io/v2/serverless/{id}"

payload = {
    "workers": {
        "min": 1,
        "max": 10,
        "idleTimeout": 10
    },
    "scaling": {
        "type": "QUEUE_DELAY",
        "queueDelay": 8
    }
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    workers: {min: 1, max: 10, idleTimeout: 10},
    scaling: {type: 'QUEUE_DELAY', queueDelay: 8}
  })
};

fetch('https://api.runpod.io/v2/serverless/{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://api.runpod.io/v2/serverless/{id}",
  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([
    'workers' => [
        'min' => 1,
        'max' => 10,
        'idleTimeout' => 10
    ],
    'scaling' => [
        'type' => 'QUEUE_DELAY',
        'queueDelay' => 8
    ]
  ]),
  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://api.runpod.io/v2/serverless/{id}"

	payload := strings.NewReader("{\n  \"workers\": {\n    \"min\": 1,\n    \"max\": 10,\n    \"idleTimeout\": 10\n  },\n  \"scaling\": {\n    \"type\": \"QUEUE_DELAY\",\n    \"queueDelay\": 8\n  }\n}")

	req, _ := http.NewRequest("PATCH", 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.patch("https://api.runpod.io/v2/serverless/{id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"workers\": {\n    \"min\": 1,\n    \"max\": 10,\n    \"idleTimeout\": 10\n  },\n  \"scaling\": {\n    \"type\": \"QUEUE_DELAY\",\n    \"queueDelay\": 8\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.runpod.io/v2/serverless/{id}")

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

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"workers\": {\n    \"min\": 1,\n    \"max\": 10,\n    \"idleTimeout\": 10\n  },\n  \"scaling\": {\n    \"type\": \"QUEUE_DELAY\",\n    \"queueDelay\": 8\n  }\n}"

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

{
  "id": "4m7x2k9q",
  "name": "image-generator",
  "type": "QUEUE",
  "requestUrls": {
    "run": "https://api.runpod.ai/v2/4m7x2k9q/run",
    "runSync": "https://api.runpod.ai/v2/4m7x2k9q/runsync",
    "status": "https://api.runpod.ai/v2/4m7x2k9q/status/{job_id}",
    "stream": "https://api.runpod.ai/v2/4m7x2k9q/stream/{job_id}",
    "cancel": "https://api.runpod.ai/v2/4m7x2k9q/cancel/{job_id}",
    "retry": "https://api.runpod.ai/v2/4m7x2k9q/retry/{job_id}",
    "purgeQueue": "https://api.runpod.ai/v2/4m7x2k9q/purge-queue",
    "health": "https://api.runpod.ai/v2/4m7x2k9q/health"
  },
  "image": "runpod/pytorch:1.0.2-cu1281-torch280-ubuntu2404",
  "args": "",
  "disk": 20,
  "ports": [
    "8000/http"
  ],
  "env": {
    "MODEL_NAME": "sdxl"
  },
  "registry": null,
  "gpu": {
    "pools": [
      "ADA_24"
    ],
    "count": 1,
    "allowedCudaVersions": [],
    "minCudaVersion": null
  },
  "workers": {
    "min": 1,
    "max": 10,
    "idleTimeout": 10
  },
  "scaling": {
    "type": "QUEUE_DELAY",
    "queueDelay": 8
  },
  "dataCenterIds": [
    "US-KS-2"
  ],
  "networkVolumes": [
    "2q9m7x4c"
  ],
  "timeout": 300000,
  "flashboot": "OFF",
  "createdAt": "2026-06-01T12:00:00Z"
}

{
  "title": "Bad Request",
  "status": 400,
  "detail": "request could not be processed"
}

{
  "title": "Unauthorized",
  "status": 401,
  "detail": "missing bearer token"
}

{
  "title": "Forbidden",
  "status": 403,
  "detail": "access denied"
}

{
  "title": "Not Found",
  "status": 404,
  "detail": "resource not found"
}

{
  "title": "Unprocessable Entity",
  "status": 422,
  "detail": "Request validation failed."
}

{
  "title": "Too Many Requests",
  "status": 429,
  "detail": "rate limit exceeded for the minute window"
}

{
  "title": "<string>",
  "status": 123,
  "detail": "<string>",
  "errors": [
    "<string>"
  ]
}

API v2

Account

Pods

Clusters

Serverless

Templates

Network Volumes

Registries

Catalog

Billing

Update a serverless endpoint

Authorizations

Path Parameters

Body

Response