Modify App

curl --request PATCH \
  --url https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "cerebrium_toml": "<string>",
  "compute": "<array>",
  "computeTier": "<string>",
  "containerRuntime": "<string>",
  "cooldownPeriodSeconds": 123,
  "cpu": "<string>",
  "deploymentInitializationTimeout": 123,
  "disableAuth": true,
  "entrypoint": "<array>",
  "evaluationIntervalSeconds": 123,
  "gpuCount": 123,
  "healthcheckEndpoint": "<string>",
  "loadBalancingAlgorithm": "<string>",
  "maxReplicaCount": 123,
  "memory": "<string>",
  "minReplicaCount": 123,
  "port": 123,
  "readycheckEndpoint": "<string>",
  "replicaConcurrency": 123,
  "responseGracePeriodSeconds": 123,
  "rollOutDurationSeconds": 123,
  "runtime": "<string>",
  "scalingBuffer": 123,
  "scalingMetric": "<string>",
  "scalingTarget": 123
}
'

import requests

url = "https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id}"

payload = {
    "cerebrium_toml": "<string>",
    "compute": "<array>",
    "computeTier": "<string>",
    "containerRuntime": "<string>",
    "cooldownPeriodSeconds": 123,
    "cpu": "<string>",
    "deploymentInitializationTimeout": 123,
    "disableAuth": True,
    "entrypoint": "<array>",
    "evaluationIntervalSeconds": 123,
    "gpuCount": 123,
    "healthcheckEndpoint": "<string>",
    "loadBalancingAlgorithm": "<string>",
    "maxReplicaCount": 123,
    "memory": "<string>",
    "minReplicaCount": 123,
    "port": 123,
    "readycheckEndpoint": "<string>",
    "replicaConcurrency": 123,
    "responseGracePeriodSeconds": 123,
    "rollOutDurationSeconds": 123,
    "runtime": "<string>",
    "scalingBuffer": 123,
    "scalingMetric": "<string>",
    "scalingTarget": 123
}
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({
    cerebrium_toml: '<string>',
    compute: '<array>',
    computeTier: '<string>',
    containerRuntime: '<string>',
    cooldownPeriodSeconds: 123,
    cpu: '<string>',
    deploymentInitializationTimeout: 123,
    disableAuth: true,
    entrypoint: '<array>',
    evaluationIntervalSeconds: 123,
    gpuCount: 123,
    healthcheckEndpoint: '<string>',
    loadBalancingAlgorithm: '<string>',
    maxReplicaCount: 123,
    memory: '<string>',
    minReplicaCount: 123,
    port: 123,
    readycheckEndpoint: '<string>',
    replicaConcurrency: 123,
    responseGracePeriodSeconds: 123,
    rollOutDurationSeconds: 123,
    runtime: '<string>',
    scalingBuffer: 123,
    scalingMetric: '<string>',
    scalingTarget: 123
  })
};

fetch('https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_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://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_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([
    'cerebrium_toml' => '<string>',
    'compute' => '<array>',
    'computeTier' => '<string>',
    'containerRuntime' => '<string>',
    'cooldownPeriodSeconds' => 123,
    'cpu' => '<string>',
    'deploymentInitializationTimeout' => 123,
    'disableAuth' => true,
    'entrypoint' => '<array>',
    'evaluationIntervalSeconds' => 123,
    'gpuCount' => 123,
    'healthcheckEndpoint' => '<string>',
    'loadBalancingAlgorithm' => '<string>',
    'maxReplicaCount' => 123,
    'memory' => '<string>',
    'minReplicaCount' => 123,
    'port' => 123,
    'readycheckEndpoint' => '<string>',
    'replicaConcurrency' => 123,
    'responseGracePeriodSeconds' => 123,
    'rollOutDurationSeconds' => 123,
    'runtime' => '<string>',
    'scalingBuffer' => 123,
    'scalingMetric' => '<string>',
    'scalingTarget' => 123
  ]),
  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://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id}"

	payload := strings.NewReader("{\n  \"cerebrium_toml\": \"<string>\",\n  \"compute\": \"<array>\",\n  \"computeTier\": \"<string>\",\n  \"containerRuntime\": \"<string>\",\n  \"cooldownPeriodSeconds\": 123,\n  \"cpu\": \"<string>\",\n  \"deploymentInitializationTimeout\": 123,\n  \"disableAuth\": true,\n  \"entrypoint\": \"<array>\",\n  \"evaluationIntervalSeconds\": 123,\n  \"gpuCount\": 123,\n  \"healthcheckEndpoint\": \"<string>\",\n  \"loadBalancingAlgorithm\": \"<string>\",\n  \"maxReplicaCount\": 123,\n  \"memory\": \"<string>\",\n  \"minReplicaCount\": 123,\n  \"port\": 123,\n  \"readycheckEndpoint\": \"<string>\",\n  \"replicaConcurrency\": 123,\n  \"responseGracePeriodSeconds\": 123,\n  \"rollOutDurationSeconds\": 123,\n  \"runtime\": \"<string>\",\n  \"scalingBuffer\": 123,\n  \"scalingMetric\": \"<string>\",\n  \"scalingTarget\": 123\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://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"cerebrium_toml\": \"<string>\",\n  \"compute\": \"<array>\",\n  \"computeTier\": \"<string>\",\n  \"containerRuntime\": \"<string>\",\n  \"cooldownPeriodSeconds\": 123,\n  \"cpu\": \"<string>\",\n  \"deploymentInitializationTimeout\": 123,\n  \"disableAuth\": true,\n  \"entrypoint\": \"<array>\",\n  \"evaluationIntervalSeconds\": 123,\n  \"gpuCount\": 123,\n  \"healthcheckEndpoint\": \"<string>\",\n  \"loadBalancingAlgorithm\": \"<string>\",\n  \"maxReplicaCount\": 123,\n  \"memory\": \"<string>\",\n  \"minReplicaCount\": 123,\n  \"port\": 123,\n  \"readycheckEndpoint\": \"<string>\",\n  \"replicaConcurrency\": 123,\n  \"responseGracePeriodSeconds\": 123,\n  \"rollOutDurationSeconds\": 123,\n  \"runtime\": \"<string>\",\n  \"scalingBuffer\": 123,\n  \"scalingMetric\": \"<string>\",\n  \"scalingTarget\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_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  \"cerebrium_toml\": \"<string>\",\n  \"compute\": \"<array>\",\n  \"computeTier\": \"<string>\",\n  \"containerRuntime\": \"<string>\",\n  \"cooldownPeriodSeconds\": 123,\n  \"cpu\": \"<string>\",\n  \"deploymentInitializationTimeout\": 123,\n  \"disableAuth\": true,\n  \"entrypoint\": \"<array>\",\n  \"evaluationIntervalSeconds\": 123,\n  \"gpuCount\": 123,\n  \"healthcheckEndpoint\": \"<string>\",\n  \"loadBalancingAlgorithm\": \"<string>\",\n  \"maxReplicaCount\": 123,\n  \"memory\": \"<string>\",\n  \"minReplicaCount\": 123,\n  \"port\": 123,\n  \"readycheckEndpoint\": \"<string>\",\n  \"replicaConcurrency\": 123,\n  \"responseGracePeriodSeconds\": 123,\n  \"rollOutDurationSeconds\": 123,\n  \"runtime\": \"<string>\",\n  \"scalingBuffer\": 123,\n  \"scalingMetric\": \"<string>\",\n  \"scalingTarget\": 123\n}"

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

{
  "app": {},
  "message": "<string>",
  "self": "<string>",
  "success": true
}

{
  "message": "<string>"
}

{
  "message": "<string>"
}

PATCH

projects

{project_id}

apps

{app_id}

Modify App

curl --request PATCH \
  --url https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "cerebrium_toml": "<string>",
  "compute": "<array>",
  "computeTier": "<string>",
  "containerRuntime": "<string>",
  "cooldownPeriodSeconds": 123,
  "cpu": "<string>",
  "deploymentInitializationTimeout": 123,
  "disableAuth": true,
  "entrypoint": "<array>",
  "evaluationIntervalSeconds": 123,
  "gpuCount": 123,
  "healthcheckEndpoint": "<string>",
  "loadBalancingAlgorithm": "<string>",
  "maxReplicaCount": 123,
  "memory": "<string>",
  "minReplicaCount": 123,
  "port": 123,
  "readycheckEndpoint": "<string>",
  "replicaConcurrency": 123,
  "responseGracePeriodSeconds": 123,
  "rollOutDurationSeconds": 123,
  "runtime": "<string>",
  "scalingBuffer": 123,
  "scalingMetric": "<string>",
  "scalingTarget": 123
}
'

import requests

url = "https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id}"

payload = {
    "cerebrium_toml": "<string>",
    "compute": "<array>",
    "computeTier": "<string>",
    "containerRuntime": "<string>",
    "cooldownPeriodSeconds": 123,
    "cpu": "<string>",
    "deploymentInitializationTimeout": 123,
    "disableAuth": True,
    "entrypoint": "<array>",
    "evaluationIntervalSeconds": 123,
    "gpuCount": 123,
    "healthcheckEndpoint": "<string>",
    "loadBalancingAlgorithm": "<string>",
    "maxReplicaCount": 123,
    "memory": "<string>",
    "minReplicaCount": 123,
    "port": 123,
    "readycheckEndpoint": "<string>",
    "replicaConcurrency": 123,
    "responseGracePeriodSeconds": 123,
    "rollOutDurationSeconds": 123,
    "runtime": "<string>",
    "scalingBuffer": 123,
    "scalingMetric": "<string>",
    "scalingTarget": 123
}
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({
    cerebrium_toml: '<string>',
    compute: '<array>',
    computeTier: '<string>',
    containerRuntime: '<string>',
    cooldownPeriodSeconds: 123,
    cpu: '<string>',
    deploymentInitializationTimeout: 123,
    disableAuth: true,
    entrypoint: '<array>',
    evaluationIntervalSeconds: 123,
    gpuCount: 123,
    healthcheckEndpoint: '<string>',
    loadBalancingAlgorithm: '<string>',
    maxReplicaCount: 123,
    memory: '<string>',
    minReplicaCount: 123,
    port: 123,
    readycheckEndpoint: '<string>',
    replicaConcurrency: 123,
    responseGracePeriodSeconds: 123,
    rollOutDurationSeconds: 123,
    runtime: '<string>',
    scalingBuffer: 123,
    scalingMetric: '<string>',
    scalingTarget: 123
  })
};

fetch('https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_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://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_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([
    'cerebrium_toml' => '<string>',
    'compute' => '<array>',
    'computeTier' => '<string>',
    'containerRuntime' => '<string>',
    'cooldownPeriodSeconds' => 123,
    'cpu' => '<string>',
    'deploymentInitializationTimeout' => 123,
    'disableAuth' => true,
    'entrypoint' => '<array>',
    'evaluationIntervalSeconds' => 123,
    'gpuCount' => 123,
    'healthcheckEndpoint' => '<string>',
    'loadBalancingAlgorithm' => '<string>',
    'maxReplicaCount' => 123,
    'memory' => '<string>',
    'minReplicaCount' => 123,
    'port' => 123,
    'readycheckEndpoint' => '<string>',
    'replicaConcurrency' => 123,
    'responseGracePeriodSeconds' => 123,
    'rollOutDurationSeconds' => 123,
    'runtime' => '<string>',
    'scalingBuffer' => 123,
    'scalingMetric' => '<string>',
    'scalingTarget' => 123
  ]),
  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://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id}"

	payload := strings.NewReader("{\n  \"cerebrium_toml\": \"<string>\",\n  \"compute\": \"<array>\",\n  \"computeTier\": \"<string>\",\n  \"containerRuntime\": \"<string>\",\n  \"cooldownPeriodSeconds\": 123,\n  \"cpu\": \"<string>\",\n  \"deploymentInitializationTimeout\": 123,\n  \"disableAuth\": true,\n  \"entrypoint\": \"<array>\",\n  \"evaluationIntervalSeconds\": 123,\n  \"gpuCount\": 123,\n  \"healthcheckEndpoint\": \"<string>\",\n  \"loadBalancingAlgorithm\": \"<string>\",\n  \"maxReplicaCount\": 123,\n  \"memory\": \"<string>\",\n  \"minReplicaCount\": 123,\n  \"port\": 123,\n  \"readycheckEndpoint\": \"<string>\",\n  \"replicaConcurrency\": 123,\n  \"responseGracePeriodSeconds\": 123,\n  \"rollOutDurationSeconds\": 123,\n  \"runtime\": \"<string>\",\n  \"scalingBuffer\": 123,\n  \"scalingMetric\": \"<string>\",\n  \"scalingTarget\": 123\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://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"cerebrium_toml\": \"<string>\",\n  \"compute\": \"<array>\",\n  \"computeTier\": \"<string>\",\n  \"containerRuntime\": \"<string>\",\n  \"cooldownPeriodSeconds\": 123,\n  \"cpu\": \"<string>\",\n  \"deploymentInitializationTimeout\": 123,\n  \"disableAuth\": true,\n  \"entrypoint\": \"<array>\",\n  \"evaluationIntervalSeconds\": 123,\n  \"gpuCount\": 123,\n  \"healthcheckEndpoint\": \"<string>\",\n  \"loadBalancingAlgorithm\": \"<string>\",\n  \"maxReplicaCount\": 123,\n  \"memory\": \"<string>\",\n  \"minReplicaCount\": 123,\n  \"port\": 123,\n  \"readycheckEndpoint\": \"<string>\",\n  \"replicaConcurrency\": 123,\n  \"responseGracePeriodSeconds\": 123,\n  \"rollOutDurationSeconds\": 123,\n  \"runtime\": \"<string>\",\n  \"scalingBuffer\": 123,\n  \"scalingMetric\": \"<string>\",\n  \"scalingTarget\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://rest.cerebrium.ai/v2/projects/{project_id}/apps/{app_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  \"cerebrium_toml\": \"<string>\",\n  \"compute\": \"<array>\",\n  \"computeTier\": \"<string>\",\n  \"containerRuntime\": \"<string>\",\n  \"cooldownPeriodSeconds\": 123,\n  \"cpu\": \"<string>\",\n  \"deploymentInitializationTimeout\": 123,\n  \"disableAuth\": true,\n  \"entrypoint\": \"<array>\",\n  \"evaluationIntervalSeconds\": 123,\n  \"gpuCount\": 123,\n  \"healthcheckEndpoint\": \"<string>\",\n  \"loadBalancingAlgorithm\": \"<string>\",\n  \"maxReplicaCount\": 123,\n  \"memory\": \"<string>\",\n  \"minReplicaCount\": 123,\n  \"port\": 123,\n  \"readycheckEndpoint\": \"<string>\",\n  \"replicaConcurrency\": 123,\n  \"responseGracePeriodSeconds\": 123,\n  \"rollOutDurationSeconds\": 123,\n  \"runtime\": \"<string>\",\n  \"scalingBuffer\": 123,\n  \"scalingMetric\": \"<string>\",\n  \"scalingTarget\": 123\n}"

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

{
  "app": {},
  "message": "<string>",
  "self": "<string>",
  "success": true
}

{
  "message": "<string>"
}

{
  "message": "<string>"
}

Authorizations

Authorization

string

header

required

Service Account Token authentication. To authenticate API requests:

Create a Service Account Token:
- Go to the Cerebrium Dashboard and open the API Keys page
- Click Create Service Account, name it (e.g., "GitHub Actions CI/CD"), choose an expiry date, and click Create
- Copy the token generated for the desired service account
Use the Token: Include the service account token in the Authorization header of API requests: Authorization: Bearer <your-service-account-token>
Best Practices:
- Create separate service accounts for different environments (dev, staging, prod)
- Store tokens securely as secrets in consuming applications or workflows
- Set appropriate expiry dates and rotate tokens regularly
- Never commit tokens to source control

For CI/CD integration examples, see the CI/CD documentation.

Path Parameters

project_id

string

required

app_id

string

required

Body

application/json

cerebrium_toml

string

Verbatim contents of the cerebrium.toml configuration file.

compute

array

Compute type(s) for the app, in priority order. A single value or a list of up to 5. Valid values: ADA_L4, ADA_L40, AMPERE_A10, AMPERE_A100_40GB, AMPERE_A100_80GB, HOPPER_H100, HOPPER_H200, BLACKWELL_B200, BLACKWELL_RTX6000, CPU, INF2, TRN1, TURING_T4.

computeTier

string

Compute tier for the app. Valid values: interruptible, protected.

containerRuntime

string

Container runtime version. Valid values: v1, v2.

cooldownPeriodSeconds

integer

Cooldown period in seconds before an idle replica scales down. Range: 1-3600.

cpu

string

Number of CPU cores to allocate, as a string value.

deploymentInitializationTimeout

integer

Maximum time in seconds to wait for a deployment to initialize. Range: 60-900.

disableAuth

boolean

Disable authentication on the app endpoint.

entrypoint

array

Command to start a custom runtime app, as a list of strings.

evaluationIntervalSeconds

integer

Interval in seconds between autoscaling evaluations. Range: 6-300.

gpuCount

integer

Number of GPUs allocated. Range: 0-8.

healthcheckEndpoint

string

HTTP endpoint used to check that a custom runtime app is healthy.

loadBalancingAlgorithm

string

Load balancing algorithm. Valid values: round-robin, first-available, min-connections, random-choice-2.

maxReplicaCount

integer

Maximum number of replicas. Range: 1-2000.

memory

string

Memory allocation in GB, as a string value.

minReplicaCount

integer

Minimum number of replicas. Range: 0-2000.

port

integer

Port the app listens on. Range: 0-65535.

readycheckEndpoint

string

HTTP endpoint used to check that a custom runtime app is ready to receive traffic.

replicaConcurrency

integer

Maximum concurrent requests per replica. Range: 1-1000000.

responseGracePeriodSeconds

integer

Grace period in seconds for in-flight requests when a replica stops. Range: 16-43200.

rollOutDurationSeconds

integer

Duration in seconds over which to roll out a new version. Range: 1-21600.

runtime

string

App runtime. Valid values: cortex, custom.

scalingBuffer

integer

Number of extra replicas to keep available beyond current demand. Must be >= 0.

scalingMetric

string

Metric used for autoscaling. Valid values: cpu_utilization, memory_utilization, requests_per_second, concurrency_utilization.

scalingTarget

integer

Target value for the scaling metric. Must be > 0.

Response

Confirmation that the app update was accepted.

app

object

The app configuration after the update is applied, including appId, projectId, hardware, cpu, memory, gpuCount, scaling settings, runtime settings, and region.

message

string

Status message for the update.

self

string

URL of the updated app resource.

success

boolean

Whether the update request was accepted.

⌘I

Builds

Projects

API Keys

Apps

Containers

Metrics

Runs

Secrets

Billing

Custom Domains

Subscriptions

Service Accounts

Users

Volumes

Files

Cerebrium Run

Integrations

Modify App

Authorizations

Path Parameters

Body

Response