PUT
/
models
/
{modelName}
/
deployments
/
{environmentName}

Authorizations

Authorization
string
headerrequired

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

modelName
string
required

Name of the model

environmentName
string
required

Name of the environment

Body

application/json

An instance of a model, deployed in a specific environment

created_at
string

The date and time when the resource was created

created_by
string

The user or service account who created the resource

updated_at
string

The date and time when the resource was updated

updated_by
string

The user or service account who updated the resource

enabled
boolean

If false, the model deployment will not be active nor serve requests

environment
string

The name of the environment in which the model deployment is deployed

flavors
object[]

The hardware flavor(s) on which this model deployment can run. This should be a subset of the flavors allowed by the environment policies, and should not mix GPU and non-GPU flavors.

integration_connections
string[]

The integration connections for the model deployment

labels
object | null

Labels

metric_port
integer

The port to serve the metrics on

model
string

The name of the parent model

model_provider_ref
object

The reference for the origin of the model

pod_template
object

The pod template for the deployment. Should be a Kubernetes PodTemplateSpec

policies
string[]

The policies that are attached to the model deployment directly

runtime
object

Configurations that describe which model is being served and how it is served

serverless_config
object

The configuration for scaling the model deployment

serving_port
integer

The port to serve the model on

workspace
string

The workspace the model deployment belongs to

Response

200 - application/json

An instance of a model, deployed in a specific environment

created_at
string

The date and time when the resource was created

created_by
string

The user or service account who created the resource

updated_at
string

The date and time when the resource was updated

updated_by
string

The user or service account who updated the resource

enabled
boolean

If false, the model deployment will not be active nor serve requests

environment
string

The name of the environment in which the model deployment is deployed

flavors
object[]

The hardware flavor(s) on which this model deployment can run. This should be a subset of the flavors allowed by the environment policies, and should not mix GPU and non-GPU flavors.

integration_connections
string[]

The integration connections for the model deployment

labels
object | null

Labels

metric_port
integer

The port to serve the metrics on

model
string

The name of the parent model

model_provider_ref
object

The reference for the origin of the model

pod_template
object

The pod template for the deployment. Should be a Kubernetes PodTemplateSpec

policies
string[]

The policies that are attached to the model deployment directly

runtime
object

Configurations that describe which model is being served and how it is served

serverless_config
object

The configuration for scaling the model deployment

serving_port
integer

The port to serve the model on

workspace
string

The workspace the model deployment belongs to