Reference
Inference API
Management API
Create environment
Creates an environment for the specified model and returns the environment.
curl --request POST \
--url https://api.baseten.co/v1/models/{model_id}/environments \
--header "Authorization: Api-Key $BASETEN_API_KEY" \
--data '{
"name": "staging",
"autoscaling_settings": {
"autoscaling_window": 800,
"concurrency_target": 3,
"max_replica": 2,
"min_replica": 1,
"scale_down_delay": 60,
"target_utilization_percentage": null
},
"promotion_settings": {
"ramp_up_duration_seconds": 600,
"ramp_up_while_promoting": true,
"redeploy_on_promotion": true,
"rolling_deploy": true,
"rolling_deploy_config": null
}
}'{
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"model_id": "<string>",
"current_deployment": {
"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
},
"instance_type_name": "<string>",
"environment": "<string>"
},
"autoscaling_settings": {
"min_replica": 123,
"max_replica": 123,
"autoscaling_window": 123,
"scale_down_delay": 123,
"concurrency_target": 123,
"target_utilization_percentage": 123
},
"promotion_settings": {
"redeploy_on_promotion": true,
"rolling_deploy": true,
"rolling_deploy_config": {
"rolling_deploy_strategy": "REPLICA",
"max_surge_percent": 20,
"max_unavailable_percent": 0,
"stabilization_time_seconds": 0,
"promotion_cleanup_strategy": "SCALE_TO_ZERO"
},
"ramp_up_while_promoting": true,
"ramp_up_duration_seconds": 600
},
"instance_type": {
"id": "<string>",
"name": "<string>",
"memory_limit_mib": 123,
"millicpu_limit": 123,
"gpu_count": 123,
"gpu_type": "<string>",
"gpu_memory_limit_mib": 123
}
}Authorizations
You must specify the scheme 'Api-Key' in the Authorization header. For example, Authorization: Api-Key <Your_Api_Key>
Path Parameters
Body
A request to create an environment.
Name of the environment
Autoscaling settings for the environment
Show child attributes
Show child attributes
Minimum number of replicas
0
Maximum number of replicas
7
Timeframe of traffic considered for autoscaling decisions
600
Waiting period before scaling down any active replica
120
Number of requests per replica before scaling up
2
Target utilization percentage for scaling up/down.
70
{
"autoscaling_window": 800,
"concurrency_target": 3,
"max_replica": 2,
"min_replica": 1,
"scale_down_delay": 60,
"target_utilization_percentage": null
}Promotion settings for the environment
Show child attributes
Show child attributes
Whether to deploy on all promotions. Enabling this flag allows model code to safely handle environment-specific logic. When a deployment is promoted, a new deployment will be created with a copy of the image.
true
Whether the environment should rely on rolling deploy orchestration.
true
Rolling deploy configuration for promotions
Show child attributes
Show child attributes
The rolling deploy strategy to use for promotions.
REPLICA "REPLICA"
The maximum surge percentage for rolling deploys.
20
The maximum unavailable percentage for rolling deploys.
20
The stabilization time in seconds for rolling deploys.
300
The promotion cleanup strategy to use for rolling deploys.
KEEP, SCALE_TO_ZERO "SCALE_TO_ZERO"
Whether to ramp up traffic while promoting
true
Duration of the ramp up in seconds
600
{
"ramp_up_duration_seconds": 600,
"ramp_up_while_promoting": true,
"redeploy_on_promotion": true,
"rolling_deploy": true,
"rolling_deploy_config": null
}Response
Environment for oracles.
Environment for oracles.
Name of the environment
Time the environment was created in ISO 8601 format
Unique identifier of the model
Current deployment of the environment
Show child attributes
Show child attributes
Unique identifier of the deployment
Time the deployment was created in ISO 8601 format
Name of the deployment
Unique identifier of the model
Whether the deployment is the production deployment of the model
Whether the deployment is the development deployment of the model
Status of the deployment
BUILDING, DEPLOYING, DEPLOY_FAILED, LOADING_MODEL, ACTIVE, UNHEALTHY, BUILD_FAILED, BUILD_STOPPED, DEACTIVATING, INACTIVE, FAILED, UPDATING, SCALED_TO_ZERO, WAKING_UP Number of active replicas
Autoscaling settings for the deployment. If null, the model has not finished deploying
Show child attributes
Show child attributes
Minimum number of replicas
Maximum number of replicas
Timeframe of traffic considered for autoscaling decisions
Waiting period before scaling down any active replica
Number of requests per replica before scaling up
Target utilization percentage for scaling up/down.
Name of the instance type the model deployment is running on
The environment associated with the deployment
Autoscaling settings for the environment
Show child attributes
Show child attributes
Minimum number of replicas
Maximum number of replicas
Timeframe of traffic considered for autoscaling decisions
Waiting period before scaling down any active replica
Number of requests per replica before scaling up
Target utilization percentage for scaling up/down.
Promotion settings for the environment
Show child attributes
Show child attributes
Whether to deploy on all promotions. Enabling this flag allows model code to safely handle environment-specific logic. When a deployment is promoted, a new deployment will be created with a copy of the image.
true
Whether the environment should rely on rolling deploy orchestration.
true
Rolling deploy configuration for promotions
Show child attributes
Show child attributes
The rolling deploy strategy to use for promotions.
REPLICA The maximum surge percentage for rolling deploys.
The maximum unavailable percentage for rolling deploys.
The stabilization time in seconds for rolling deploys.
The promotion cleanup strategy to use for rolling deploys.
KEEP, SCALE_TO_ZERO Whether to ramp up traffic while promoting
true
Duration of the ramp up in seconds
600
Instance type for the environment
Show child attributes
Show child attributes
Identifier string for the instance type
Display name of the instance type
Memory limit of the instance type in Mebibytes
CPU limit of the instance type in millicpu
Number of GPUs on the instance type
Type of GPU on the instance type
Memory limit of the GPU on the instance type in Mebibytes
Was this page helpful?
curl --request POST \
--url https://api.baseten.co/v1/models/{model_id}/environments \
--header "Authorization: Api-Key $BASETEN_API_KEY" \
--data '{
"name": "staging",
"autoscaling_settings": {
"autoscaling_window": 800,
"concurrency_target": 3,
"max_replica": 2,
"min_replica": 1,
"scale_down_delay": 60,
"target_utilization_percentage": null
},
"promotion_settings": {
"ramp_up_duration_seconds": 600,
"ramp_up_while_promoting": true,
"redeploy_on_promotion": true,
"rolling_deploy": true,
"rolling_deploy_config": null
}
}'{
"name": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"model_id": "<string>",
"current_deployment": {
"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
},
"instance_type_name": "<string>",
"environment": "<string>"
},
"autoscaling_settings": {
"min_replica": 123,
"max_replica": 123,
"autoscaling_window": 123,
"scale_down_delay": 123,
"concurrency_target": 123,
"target_utilization_percentage": 123
},
"promotion_settings": {
"redeploy_on_promotion": true,
"rolling_deploy": true,
"rolling_deploy_config": {
"rolling_deploy_strategy": "REPLICA",
"max_surge_percent": 20,
"max_unavailable_percent": 0,
"stabilization_time_seconds": 0,
"promotion_cleanup_strategy": "SCALE_TO_ZERO"
},
"ramp_up_while_promoting": true,
"ramp_up_duration_seconds": 600
},
"instance_type": {
"id": "<string>",
"name": "<string>",
"memory_limit_mib": 123,
"millicpu_limit": 123,
"gpu_count": 123,
"gpu_type": "<string>",
"gpu_memory_limit_mib": 123
}
}