Promote a deployment to production

POST

models

{model_id}

deployments

{deployment_id}

promote

cURL

curl --request POST \
--url https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote \
--header "Authorization: Bearer $BASETEN_API_KEY" \
--data '{
  "scale_down_previous_production": true,
  "preserve_env_instance_type": true,
  "environment_settings_update": {
    "autoscaling_settings": {
      "max_replica": 4,
      "min_replica": 2
    }
  },
  "promotion_settings_override": {
    "rolling_deploy_config": {
      "max_surge_percent": 50
    }
  }
}'

import requests
import os
API_KEY = os.environ.get("BASETEN_API_KEY", "<YOUR_API_KEY>")
url = "https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote"

headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.request(
    "POST",
    url,
    headers=headers,
    json={'scale_down_previous_production': True, 'preserve_env_instance_type': True, 'environment_settings_update': {'autoscaling_settings': {'max_replica': 4, 'min_replica': 2}}, 'promotion_settings_override': {'rolling_deploy_config': {'max_surge_percent': 50}}}
)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    scale_down_previous_production: true,
    preserve_env_instance_type: true,
    environment_settings_update: {autoscaling_settings: {max_replica: 4, min_replica: 2}},
    promotion_settings_override: {rolling_deploy_config: {max_surge_percent: 50}}
  })
};

fetch('https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote', 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.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'scale_down_previous_production' => true,
    'preserve_env_instance_type' => true,
    'environment_settings_update' => [
        'autoscaling_settings' => [
                'max_replica' => 4,
                'min_replica' => 2
        ]
    ],
    'promotion_settings_override' => [
        'rolling_deploy_config' => [
                'max_surge_percent' => 50
        ]
    ]
  ]),
  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.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote"

	payload := strings.NewReader("{\n  \"scale_down_previous_production\": true,\n  \"preserve_env_instance_type\": true,\n  \"environment_settings_update\": {\n    \"autoscaling_settings\": {\n      \"max_replica\": 4,\n      \"min_replica\": 2\n    }\n  },\n  \"promotion_settings_override\": {\n    \"rolling_deploy_config\": {\n      \"max_surge_percent\": 50\n    }\n  }\n}")

	req, _ := http.NewRequest("POST", 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.post("https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"scale_down_previous_production\": true,\n  \"preserve_env_instance_type\": true,\n  \"environment_settings_update\": {\n    \"autoscaling_settings\": {\n      \"max_replica\": 4,\n      \"min_replica\": 2\n    }\n  },\n  \"promotion_settings_override\": {\n    \"rolling_deploy_config\": {\n      \"max_surge_percent\": 50\n    }\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"scale_down_previous_production\": true,\n  \"preserve_env_instance_type\": true,\n  \"environment_settings_update\": {\n    \"autoscaling_settings\": {\n      \"max_replica\": 4,\n      \"min_replica\": 2\n    }\n  },\n  \"promotion_settings_override\": {\n    \"rolling_deploy_config\": {\n      \"max_surge_percent\": 50\n    }\n  }\n}"

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

{
  "id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "name": "<string>",
  "model_id": "<string>",
  "is_production": true,
  "is_development": true,
  "status": "BUILDING",
  "active_replica_count": 123,
  "autoscaling_settings": {
    "min_replica": 123,
    "max_replica": 123,
    "autoscaling_window": 123,
    "scale_down_delay": 123,
    "concurrency_target": 123,
    "target_utilization_percentage": 123,
    "target_in_flight_tokens": 123,
    "max_scale_down_rate": 123
  },
  "instance_type_name": "<string>",
  "environment": "<string>",
  "request_backpressure_settings": {
    "policy": "QUEUE_ON_FULL"
  },
  "labels": {},
  "region": {
    "slug": "us",
    "display_name": "United States"
  },
  "failure_reason": "<string>"
}

Related guide: Manage the deployment lifecycle. Promotions use the production environment’s rolling deployment settings, including mixed mode.

Authorizations

Authorization

string

header

required

Send Authorization: Bearer <api_key>. The legacy Authorization: Api-Key <api_key> scheme is also accepted.

Path Parameters

model_id

string

required

deployment_id

string

required

Body

application/json

A request to promote a deployment to production.

scale_down_previous_production

boolean

default:true

Whether to scale down the previous production deployment after promoting

Example:

true

preserve_env_instance_type

boolean

default:true

Whether to use the promoting deployment's instance type or preserve target environment's instance type

Example:

true

environment_settings_update

PromotionEnvironmentSettingsUpdateV1 · object | null

Changes to the environment's settings. Omitted fields are unchanged. The promoted deployment uses the environment's current settings with these changes applied, and the environment keeps the result when the promotion completes.

Show child attributes

Example:

{
  "autoscaling_settings": { "max_replica": 4, "min_replica": 2 }
}

promotion_settings_override

UpdatePromotionSettingsV1 · object | null

Promotion settings for this promotion only. Omitted fields keep the environment's values, and the environment's promotion settings are unchanged.

Show child attributes

Example:

{
  "rolling_deploy_config": { "max_surge_percent": 50 }
}

Response

200 - application/json

A deployment of a model.

string

required

Unique identifier of the deployment

created_at

string<date-time>

required

Time the deployment was created in ISO 8601 format

name

string

required

Name of the deployment

model_id

string

required

Unique identifier of the model

is_production

boolean

required

Whether the deployment is the production deployment of the model

is_development

boolean

required

Whether the deployment is the development deployment of the model

status

enum<string>

required

Status of the deployment

Available options:

BUILDING,

DEPLOYING,

DEPLOY_FAILED,

LOADING_MODEL,

ACTIVE,

UNHEALTHY,

BUILD_FAILED,

BUILD_STOPPED,

DEACTIVATING,

INACTIVE,

FAILED,

UPDATING,

SCALED_TO_ZERO,

WAKING_UP

active_replica_count

integer

required

Number of active replicas

autoscaling_settings

AutoscalingSettingsV1 · object | null

required

Autoscaling settings for the deployment. If null, the model has not finished deploying

Show child attributes

instance_type_name

string | null

required

Name of the instance type the model deployment is running on

environment

string | null

required

The environment associated with the deployment

request_backpressure_settings

RequestBackpressureSettingsV1 · object

required

Effective request backpressure settings for the deployment.

Show child attributes

labels

Labels · object | null

User-provided key-value labels for the deployment

region

RegionV1 · object | null

The selected region for the deployment, if any

Show child attributes

failure_reason

string | null

Why the deployment failed. Set only when the status is DEPLOY_FAILED; null otherwise.

⌘I

cURL

curl --request POST \
--url https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote \
--header "Authorization: Bearer $BASETEN_API_KEY" \
--data '{
  "scale_down_previous_production": true,
  "preserve_env_instance_type": true,
  "environment_settings_update": {
    "autoscaling_settings": {
      "max_replica": 4,
      "min_replica": 2
    }
  },
  "promotion_settings_override": {
    "rolling_deploy_config": {
      "max_surge_percent": 50
    }
  }
}'

import requests
import os
API_KEY = os.environ.get("BASETEN_API_KEY", "<YOUR_API_KEY>")
url = "https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote"

headers = {"Authorization": f"Bearer {API_KEY}"}

response = requests.request(
    "POST",
    url,
    headers=headers,
    json={'scale_down_previous_production': True, 'preserve_env_instance_type': True, 'environment_settings_update': {'autoscaling_settings': {'max_replica': 4, 'min_replica': 2}}, 'promotion_settings_override': {'rolling_deploy_config': {'max_surge_percent': 50}}}
)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    scale_down_previous_production: true,
    preserve_env_instance_type: true,
    environment_settings_update: {autoscaling_settings: {max_replica: 4, min_replica: 2}},
    promotion_settings_override: {rolling_deploy_config: {max_surge_percent: 50}}
  })
};

fetch('https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote', 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.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'scale_down_previous_production' => true,
    'preserve_env_instance_type' => true,
    'environment_settings_update' => [
        'autoscaling_settings' => [
                'max_replica' => 4,
                'min_replica' => 2
        ]
    ],
    'promotion_settings_override' => [
        'rolling_deploy_config' => [
                'max_surge_percent' => 50
        ]
    ]
  ]),
  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.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote"

	payload := strings.NewReader("{\n  \"scale_down_previous_production\": true,\n  \"preserve_env_instance_type\": true,\n  \"environment_settings_update\": {\n    \"autoscaling_settings\": {\n      \"max_replica\": 4,\n      \"min_replica\": 2\n    }\n  },\n  \"promotion_settings_override\": {\n    \"rolling_deploy_config\": {\n      \"max_surge_percent\": 50\n    }\n  }\n}")

	req, _ := http.NewRequest("POST", 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.post("https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"scale_down_previous_production\": true,\n  \"preserve_env_instance_type\": true,\n  \"environment_settings_update\": {\n    \"autoscaling_settings\": {\n      \"max_replica\": 4,\n      \"min_replica\": 2\n    }\n  },\n  \"promotion_settings_override\": {\n    \"rolling_deploy_config\": {\n      \"max_surge_percent\": 50\n    }\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.baseten.co/v1/models/{model_id}/deployments/{deployment_id}/promote")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"scale_down_previous_production\": true,\n  \"preserve_env_instance_type\": true,\n  \"environment_settings_update\": {\n    \"autoscaling_settings\": {\n      \"max_replica\": 4,\n      \"min_replica\": 2\n    }\n  },\n  \"promotion_settings_override\": {\n    \"rolling_deploy_config\": {\n      \"max_surge_percent\": 50\n    }\n  }\n}"

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

{
  "id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "name": "<string>",
  "model_id": "<string>",
  "is_production": true,
  "is_development": true,
  "status": "BUILDING",
  "active_replica_count": 123,
  "autoscaling_settings": {
    "min_replica": 123,
    "max_replica": 123,
    "autoscaling_window": 123,
    "scale_down_delay": 123,
    "concurrency_target": 123,
    "target_utilization_percentage": 123,
    "target_in_flight_tokens": 123,
    "max_scale_down_rate": 123
  },
  "instance_type_name": "<string>",
  "environment": "<string>",
  "request_backpressure_settings": {
    "policy": "QUEUE_ON_FULL"
  },
  "labels": {},
  "region": {
    "slug": "us",
    "display_name": "United States"
  },
  "failure_reason": "<string>"
}

Reference

Inference API

Management API

Loops API

Training API

Frontier Gateway API

Sandbox runtime API

CLI reference

SDKs and clients

Configuration

Metrics

Integrations

Promote a deployment to production

Authorizations

Path Parameters

Body

Response