Give Feedback

doctl dedicated-inference

Generated on 1 Apr 2026 from doctl version v1.154.0

Aliases

di, dedicated-inferences

The subcommands of doctl dedicated-inference manage your dedicated inference endpoints.

Option	Description
`--help`, `-h`	Help for this command

Command	Description
doctl	doctl is a command line interface (CLI) for the DigitalOcean API.
doctl dedicated-inference create	Create a dedicated inference endpoint
doctl dedicated-inference create-token	Create an auth token for a dedicated inference endpoint
doctl dedicated-inference delete	Delete a dedicated inference endpoint
doctl dedicated-inference get	Retrieve a dedicated inference endpoint
doctl dedicated-inference get-gpu-model-config	List supported GPU model configurations
doctl dedicated-inference get-sizes	List available dedicated inference GPU sizes and pricing
doctl dedicated-inference list	List all dedicated inference endpoints
doctl dedicated-inference list-accelerators	List accelerators for a dedicated inference endpoint
doctl dedicated-inference list-tokens	List auth tokens for a dedicated inference endpoint
doctl dedicated-inference revoke-token	Revoke an auth token for a dedicated inference endpoint
doctl dedicated-inference update	Update a dedicated inference endpoint

Option	Description
`--access-token`, `-t`	API V2 access token
`--api-url`, `-u`	Override default API endpoint
`--config`, `-c`	Specify a custom config file Default:
`--context`	Specify a custom authentication context name
`--http-retry-max`	Set maximum number of retries for requests that fail with a 429 or 500-level error Default: `5`
`--http-retry-wait-max`	Set the minimum number of seconds to wait before retrying a failed request Default: `30`
`--http-retry-wait-min`	Set the maximum number of seconds to wait before retrying a failed request Default: `1`
`--interactive`	Enable interactive behavior. Defaults to true if the terminal supports it (default false) Default: `false`
`--output`, `-o`	Desired output format [text\|json] Default: `text`
`--trace`	Show a log of network activity while performing a command Default: `false`
`--verbose`, `-v`	Enable verbose output Default: `false`