Skip to main content
Create and start a new Pod on Runpod with configuration options for GPU type, storage, networking, and cloud tier.
runpodctl create pod [flags]

Example

Create a Pod with 2 RTX 4090 GPUs in the Secure Cloud with a custom container image:
runpodctl create pod --name "my-training-pod" --gpuType "RTX 4090" --gpuCount 2 --secureCloud --imageName "runpod/pytorch:2.0.1-py3.10-cuda11.8.0-devel" --containerDiskSize 50 --volumeSize 100

Flags

The following flags are available for the create pod command:
--name <value>string A custom name for your Pod to make it easy to identify and reference.
--gpuType <value>string The GPU type to use for the Pod (e.g., RTX 4090, A100 80GB, H100 SXM).
--gpuCount <number>integer • default = 1 The number of GPUs to allocate to the Pod.
--secureCloud Create the Pod in the Secure Cloud tier, which offers enterprise-grade infrastructure with enhanced reliability.
--communityCloud Create the Pod in the Community Cloud tier, which typically offers lower pricing with spot instance availability.
--imageName <value>string The Docker container image to use for the Pod (e.g., runpod/pytorch:latest).
--templateId <value>string The ID of a template to use for Pod configuration, which pre-defines the image and environment settings.
--containerDiskSize <number>integer • default = 20 The size of the container disk in gigabytes, used for temporary storage within the container.
--volumeSize <number>integer • default = 1 The size of the persistent volume in gigabytes, which retains data across Pod restarts.
--volumePath <value>string • default = /workspace The mount path for the persistent volume inside the container.
--networkVolumeId <value>string The ID of an existing network volume to attach to the Pod for shared storage across multiple Pods.
--cost <number>float The maximum price ceiling in dollars per hour. If not specified, the Pod will be created at the lowest available price.
--mem <number>integer • default = 20 The minimum system memory required in gigabytes.
--vcpu <number>integer • default = 1 The minimum number of vCPUs required for the Pod.
--env <value>string Environment variables to set in the container. Specify multiple times for multiple variables (e.g., --env KEY1=VALUE1 -env KEY2=VALUE2).
--args <value>string Additional arguments to pass to the container when it starts.
--ports <value>string Ports to expose from the container. Maximum of 1 HTTP port and 1 TCP port allowed (e.g., --ports 8888/http --ports 22/tcp).