Get a serverless endpoint

GET

serverless

{id}

curl --request GET \
  --url https://api.runpod.io/v2/serverless/{id} \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

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 => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

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

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

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::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

{
  "id": "4m7x2k9q",
  "name": "image-generator",
  "type": "LOAD_BALANCER",
  "requestUrls": {
    "base": "https://4m7x2k9q.api.runpod.ai",
    "health": "https://4m7x2k9q.api.runpod.ai/ping"
  },
  "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": 0,
    "max": 5,
    "idleTimeout": 5
  },
  "scaling": {
    "type": "REQUEST_COUNT",
    "requestCount": 4
  },
  "dataCenterIds": [
    "US-KS-2"
  ],
  "networkVolumes": [
    "2q9m7x4c"
  ],
  "timeout": 300000,
  "flashboot": "OFF",
  "createdAt": "2026-06-01T12:00:00Z"
}

{
  "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": "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

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

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

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

Get a serverless endpoint

curl --request GET \
  --url https://api.runpod.io/v2/serverless/{id} \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

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 => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

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

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

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::Get.new(url)
request["Authorization"] = 'Bearer <token>'

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

{
  "id": "4m7x2k9q",
  "name": "image-generator",
  "type": "LOAD_BALANCER",
  "requestUrls": {
    "base": "https://4m7x2k9q.api.runpod.ai",
    "health": "https://4m7x2k9q.api.runpod.ai/ping"
  },
  "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": 0,
    "max": 5,
    "idleTimeout": 5
  },
  "scaling": {
    "type": "REQUEST_COUNT",
    "requestCount": 4
  },
  "dataCenterIds": [
    "US-KS-2"
  ],
  "networkVolumes": [
    "2q9m7x4c"
  ],
  "timeout": 300000,
  "flashboot": "OFF",
  "createdAt": "2026-06-01T12:00:00Z"
}

{
  "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": "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

Authorizations

Path Parameters

Response