Create a new deployment
Create a new deployment with specified configuration
Authorization
bearerAuth In: header
Request Body
application/json
Deployment configuration
Args overrides the container's CMD. Provide as an array of arguments (e.g., ["python", "app.py"])
Autoscaling configuration. Example: {"metric": "QueueBacklogPerWorker", "target": 1.01} to scale based on queue backlog. Omit or set to null to disable autoscaling
Controls how replicas above reserved capacity behave. stable replicas stay running after scale-up; preemptible replicas may be evicted during capacity contention.
Value in
- "stable"
- "preemptible"
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)
0.1 <= valueDescription is an optional human-readable description of your deployment
EnvironmentVariables is a list of environment variables to set in the container. Each must have a name and either a value or value_from_secret
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").
Value in
- "h100-80gb"
- "h100-40gb-mig"
- "h200-140gb"
- "b200-192gb"
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)
value <= 1000MinReplicas is the minimum number of container instances to run. Defaults to 1 if not specified
Model weights to preload from Together's model registry into the container. At most one mount is supported, and it cannot be used with volumes.
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.
4 <= length <= 63Port is the container port your application listens on (e.g., 8080 for web servers). Required if your application serves traffic
1 <= value <= 65535Storage is the amount of ephemeral disk storage to allocate per container instance (e.g., 10 = 10GiB)
value <= 400TerminationGracePeriodSeconds is the time in seconds to wait for graceful shutdown before forcefully terminating the replica
Volumes is a list of volume mounts to attach to the container. Each mount must reference an existing volume by name
Response Body
application/json
application/json
application/json
curl -X POST "https://example.com/deployments" \ -H "Content-Type: application/json" \ -d '{ "gpu_type": "h100-80gb", "image": "string", "name": "string" }'{ "args": [ "string" ], "autoscaling": { "metric": "HTTPTotalRequests", "target": 0, "time_interval_minutes": 0 }, "capacity_type": "stable", "command": [ "string" ], "cpu": 0, "created_at": "2019-08-24T14:15:22Z", "description": "string", "desired_replicas": 0, "environment_variables": [ { "name": "string", "value": "string", "value_from_secret": "string" } ], "gpu_count": 0, "gpu_type": "h100-80gb", "health_check_path": "string", "id": "string", "image": "string", "max_replicas": 0, "memory": 0, "min_replicas": 0, "model_mounts": [ { "model_id": "string", "mount_path": "string", "revision_id": "string" } ], "name": "string", "object": "deployment", "port": 0, "ready_replicas": 0, "replica_events": { "property1": { "image": "string", "replica_ready_since": "string", "replica_status": "string", "replica_status_message": "string", "replica_status_reason": "string", "revision_id": "string", "volume_preload_completed_at": "string", "volume_preload_started_at": "string", "volume_preload_status": "string" }, "property2": { "image": "string", "replica_ready_since": "string", "replica_status": "string", "replica_status_message": "string", "replica_status_reason": "string", "revision_id": "string", "volume_preload_completed_at": "string", "volume_preload_started_at": "string", "volume_preload_status": "string" } }, "status": "Updating", "storage": 0, "termination_grace_period_seconds": 0, "updated_at": "2019-08-24T14:15:22Z", "volumes": [ { "mount_path": "string", "name": "string", "version": 0 } ]}