v1

latestOpenAPI 3.1.02026-07-26157321426.3 KB

Promotes a development deployment to production

Creates a new production deployment from the development deployment and returns the deployment that is building.

post/v1/models/{model_id}/deployments/development/promote

Request body

scale_down_previous_productionboolean

Whether to scale down the previous production deployment after promoting

preserve_env_instance_typeboolean

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

Example request

{
  "scale_down_previous_production": true,
  "preserve_env_instance_type": true
}

Response

idstring required

Unique identifier of the deployment

created_atstring date-time required

Time the deployment was created in ISO 8601 format

namestring required

Name of the deployment

model_idstring required

Unique identifier of the model

is_productionboolean required

Whether the deployment is the production deployment of the model

is_developmentboolean required

Whether the deployment is the development deployment of the model

status'BUILDING' | 'DEPLOYING' | 'DEPLOY_FAILED' | 'LOADING_MODEL' | 'ACTIVE' | 'UNHEALTHY' | 'BUILD_FAILED' | 'BUILD_STOPPED' | 'DEACTIVATING' | 'INACTIVE' | 'FAILED' | 'UPDATING' | 'SCALED_TO_ZERO' | 'WAKING_UP' required

The status of a deployment.

active_replica_countinteger required

Number of active replicas

instance_type_namestring nullable required

Name of the instance type the model deployment is running on

environmentstring nullable required

The environment associated with the deployment

labelsobject nullable

User-provided key-value labels for the deployment