Create the deployment.

time	status	user agent
Retrieving recent requests…

time

status

user agent

Retrieving recent requests…

201

Created

Response body

object

spec

object

cluster

string

command

string

Command is the command to run.

deployment_resource

object

deployment_source

object

DeploymentSource represents the location and type of the deployment.

env_vars

object

EnvVars is the environment variables of the deployment.

Has additional fields

framework

string

Framework is the framework of the deployment. (mosec, gradio, streamlit, other)

mosec gradio streamlit other unknown

http_probe_path

string

HTTPProbePath is the user defined path of the http probe.

string

ID holds the unique identifier of the deployment.

image_config

object

max_replicas

integer

MaxReplicas is the maximum number of replicas of the deployment.

min_replicas

integer

MinReplicas is the minimum number of replicas of the deployment.

name

string

Name is the name of the deployment. e.g. demo.
a-z0-9?

port

integer

Port is the port of the deployment.

secret

array of strings

Secret is the secret of the deployment.

secret

server_resource

string

nvidia-tesla-t4-4c-16g cpu-4c-16g nvidia-ampere-a100-40g-12c-85g nvidia-ada-l4-8c-32g nvidia-ada-l4-4-48c-192g nvidia-ada-l4-2-24c-96g

spot_instance

boolean

startup_duration

integer

StartupDuration is the startup timeout.

target_load

integer

TargetLoad is the target load of the deployment. (inflight requests per replica)

templateId

string

TemplateID is the template ID of the deployment.

zero_duration

integer

ZeroDuration is the idle timeout before scaling to zero.

status

object

available_replicas

integer

AvailableReplicas is the count of replicas ready to receive
invocations as reported by the faas-provider

build_id

string

created_at

string

CreatedAt is the time read back from the faas backend's
data store for when the function or its container was created.

endpoint

string

Endpoint is the endpoint of the deployment. e.g. https://df433125-bdaa-4180-9087-313d5f64a3d5.modelz.ai

image

string

Image is the image name of the deployment.

innocation_count

integer

InvocationCount count of invocations

phase

string

Phase is the current phase of the deployment.

replicas

integer

Replicas desired within the cluster

xxxxxxxxxx
curl --request POST \
     --url https://cloud.modelz.ai/api/v1/users/login_name/clusters/cluster_id/deployments \
     --header 'accept: application/json' \
     --header 'content-type: application/json'

201Created