Create a new deployment
Create a new deployment with specified configuration
Request body
Args overrides the container's CMD. Provide as an array of arguments (e.g., ["python", "app.py"])
Command overrides the container's ENTRYPOINT. Provide as an array (e.g., ["/bin/sh", "-c"])
CPU is the number of CPU cores to allocate per container instance (e.g., 0.1 = 100 milli cores)
Description is an optional human-readable description of your deployment
GPUCount is the number of GPUs to allocate per container instance. Defaults to 0 if not specified
GPUType specifies the GPU hardware to use (e.g., "h100-80gb").
HealthCheckPath is the HTTP path for health checks (e.g., "/health"). If set, the platform checks this endpoint to determine container health.
Image is the container image to deploy from registry.together.ai.
MaxReplicas is the maximum number of container instances. Defaults to MinReplicas if not set.
Memory is the amount of RAM to allocate per container instance in GiB (e.g., 0.5 = 512MiB)
MinReplicas is the minimum number of container instances to run. Defaults to 1 if not specified
Name is the unique identifier for your deployment. Must contain only alphanumeric characters, underscores, or hyphens (1-100 characters)
Port is the container port your application listens on (e.g., 8080 for web servers). Required if your application serves traffic
Storage is the amount of ephemeral disk storage to allocate per container instance (e.g., 10 = 10GiB)
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
Args are the arguments passed to the container's command
Command is the entrypoint command run in the container
CPU is the amount of CPU resource allocated to each replica in cores (fractional value is allowed)
CreatedAt is the ISO8601 timestamp when this deployment was created
Description provides a human-readable explanation of the deployment's purpose or content
DesiredReplicas is the number of replicas that the orchestrator is targeting
GPUCount is the number of GPUs allocated to each replica in this deployment
GPUType specifies the type of GPU requested (if any) for this deployment
HealthCheckPath is the HTTP path used for health checks of the application
ID is the unique identifier of the deployment
Image specifies the container image used for this deployment
MaxReplicas is the maximum number of replicas to run for this deployment
Memory is the amount of memory allocated to each replica in GiB (fractional value is allowed)
MinReplicas is the minimum number of replicas to run for this deployment
Name is the name of the deployment
The object type, which is always deployment.
Port is the container port that the deployment exposes
ReadyReplicas is the current number of replicas that are in the Ready state
ReplicaEvents is a mapping of replica names or IDs to their status events
Storage is the amount of storage (in MB or units as defined by the platform) allocated to each replica
TerminationGracePeriodSeconds is the time in seconds to wait for graceful shutdown before forcefully terminating the replica
UpdatedAt is the ISO8601 timestamp when this deployment was last updated
Example response
{
"autoscaling": {
"metric": "HTTPTotalRequests",
"target": 100,
"time_interval_minutes": 10
}
}