Sign in
Deployments

Create a new deployment

Create a new deployment with specified configuration

post/deployments

Request body

argsstring[]

Args overrides the container's CMD. Provide as an array of arguments (e.g., ["python", "app.py"])

commandstring[]

Command overrides the container's ENTRYPOINT. Provide as an array (e.g., ["/bin/sh", "-c"])

cpunumber

CPU is the number of CPU cores to allocate per container instance (e.g., 0.1 = 100 milli cores)

descriptionstring

Description is an optional human-readable description of your deployment

gpu_countinteger

GPUCount is the number of GPUs to allocate per container instance. Defaults to 0 if not specified

gpu_type'h100-80gb' | 'h100-40gb-mig' | 'h200-140gb' | 'b200-192gb' required

GPUType specifies the GPU hardware to use (e.g., "h100-80gb").

health_check_pathstring

HealthCheckPath is the HTTP path for health checks (e.g., "/health"). If set, the platform checks this endpoint to determine container health.

imagestring required

Image is the container image to deploy from registry.together.ai.

max_replicasinteger

MaxReplicas is the maximum number of container instances. Defaults to MinReplicas if not set.

memorynumber

Memory is the amount of RAM to allocate per container instance in GiB (e.g., 0.5 = 512MiB)

min_replicasinteger

MinReplicas is the minimum number of container instances to run. Defaults to 1 if not specified

namestring required

Name is the unique identifier for your deployment. Must contain lowercase letters, numbers, or hyphens, start with a lowercase letter or number, and be 4-63 characters. It cannot be changed.

portinteger

Port is the container port your application listens on (e.g., 8080 for web servers). Required if your application serves traffic

storageinteger

Storage is the amount of ephemeral disk storage to allocate per container instance (e.g., 10 = 10GiB)

termination_grace_period_secondsinteger

TerminationGracePeriodSeconds is the time in seconds to wait for graceful shutdown before forcefully terminating the replica

Example request

{
  "autoscaling": {
    "metric": "HTTPTotalRequests",
    "target": 100,
    "time_interval_minutes": 10
  }
}

Response

Deployment created successfully

argsstring[]

Args are the arguments passed to the container's command

commandstring[]

Command is the entrypoint command run in the container

cpunumber

CPU is the amount of CPU resource allocated to each replica in cores (fractional value is allowed)

created_atstring date-time

CreatedAt is the ISO8601 timestamp when this deployment was created

descriptionstring

Description provides a human-readable explanation of the deployment's purpose or content

desired_replicasinteger

DesiredReplicas is the number of replicas that the orchestrator is targeting

gpu_countinteger

GPUCount is the number of GPUs allocated to each replica in this deployment

gpu_type'h100-80gb' | 'h100-40gb-mig' | 'h200-140gb' | 'b200-192gb'

GPUType specifies the type of GPU requested (if any) for this deployment

health_check_pathstring

HealthCheckPath is the HTTP path used for health checks of the application

idstring

ID is the unique identifier of the deployment

imagestring

Image specifies the container image used for this deployment

max_replicasinteger

MaxReplicas is the maximum number of replicas to run for this deployment

memorynumber

Memory is the amount of memory allocated to each replica in GiB (fractional value is allowed)

min_replicasinteger

MinReplicas is the minimum number of replicas to run for this deployment

namestring

Name is the name of the deployment

object'deployment'

The object type, which is always deployment.

portinteger

Port is the container port that the deployment exposes

ready_replicasinteger

ReadyReplicas is the current number of replicas that are in the Ready state

replica_eventsobject

ReplicaEvents is a mapping of replica names or IDs to their status events

status'Updating' | 'Scaling' | 'Ready' | 'Failed' | 'ScaledToZero'
storageinteger

Storage is the amount of storage (in MB or units as defined by the platform) allocated to each replica

termination_grace_period_secondsinteger

TerminationGracePeriodSeconds is the time in seconds to wait for graceful shutdown before forcefully terminating the replica

updated_atstring date-time

UpdatedAt is the ISO8601 timestamp when this deployment was last updated

Example response

{
  "autoscaling": {
    "metric": "HTTPTotalRequests",
    "target": 100,
    "time_interval_minutes": 10
  }
}

Changes

Changed in 1 of the 14 revisions of this API.2

  • 42c9ead8f2f52See the full diff
    • ▲

      the name request property's maxLength was decreased to 63

      request-property-max-length-decreased

    • ▲

      the name request property's minLength was increased from 1 to 4

      request-property-min-length-increased