Skip to main content
Manage models in the Model Repo, including adding, uploading, listing, and removing models. 
runpodctl model <subcommand> [flags]

​
Subcommands

​
Add a model

Register a new model with the Model Repo: 
runpodctl model add --name "my-model"
To upload model files from a local directory: 
runpodctl model add --name "my-model" --model-path ./model-files

​
Add flags

​
--name
string
required
Model name.
​
--owner
string
Model owner namespace (user or team owner ID). Use this to add models to a team account.
​
--model-status
string
Initial model status.
​
--credential-type
string
Credential type (if required for model access).
​
--credential-reference
string
Credential reference (if required for model access).
​
--model-path
string
Directory containing model files to upload. When specified, all files in the directory are uploaded to the Model Repo.
​
--create-upload
bool
Create an upload session without uploading files. Use this to get upload URLs for manual file uploads.
​
--file-name
string
File name for single-file upload.
​
--file-size
string
File size in bytes for single-file upload.
​
--part-size
string
Multipart upload part size in bytes.
​
--content-type
string
Content type for the upload.
​
--graphql-timeout
duration
GraphQL request timeout. Defaults to 30 minutes for model upload operations.

​
List models

List models in your account: 
runpodctl model list
Filter by provider or name: 
runpodctl model list --provider huggingface
runpodctl model list --name "llama"

​
List flags

​
--provider
string
Filter by model provider.
​
--name
string
Filter by model name.

​
Remove a model

Remove a model from the Model Repo: 
runpodctl model remove <model-id>
You can specify the model by ID or name: 
runpodctl model remove my-model
Removing a model permanently deletes it and all associated versions from the Model Repo. This action cannot be undone.

​
Environment variables

​
RUNPOD_GRAPHQL_URL
string
Override the GraphQL API endpoint URL. Defaults to https://api.runpod.io/graphql.

​
Using model version hashes

To create a Serverless endpoint that uses a model from the Model Repo, reference the model by its version hash: 
runpodctl serverless create --template-id "tpl_abc123" --name "my-endpoint" \
  --model-reference "abc123def456"
Run runpodctl model list to find the version hash for your model.