doctl dedicated-inference create
Generated on 1 Apr 2026
from doctl version
v1.154.0
Usage
doctl dedicated-inference create [flags]Aliases
cDescription
Creates a dedicated inference endpoint on your account using a spec file in JSON or YAML format.
Use the --spec flag to provide the path to the spec file.
Optionally provide a Hugging Face access token using --hugging-face-token.
Example
The following example creates a dedicated inference endpoint using a spec file:
doctl dedicated-inference create --spec spec.yaml --hugging-face-token "hf_mytoken"
For more information, see /reference/api/reference/dedicated-inference/#dedicatedInferences_createFlags
| Option | Description |
|---|---|
--format |
Columns for output in a comma-separated list. Possible values: ID, Name, Region, Status, VPCUUID, PublicEndpoint, PrivateEndpoint, CreatedAt, UpdatedAt. |
--help, -h |
Help for this command |
--hugging-face-token |
Hugging Face token for accessing gated models (optional) |
--no-header |
Return raw data with no headers Default: false |
--spec |
Path to a dedicated inference spec in JSON or YAML format. Set to “-” to read from stdin. (required) |
Related Commands
| Command | Description |
|---|---|
| doctl dedicated-inference | Display commands for managing dedicated inference endpoints |
Global Flags
| 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 |