Create

1 min readUpdated 30 September 2026

Provisions a new inference instance on Vultrs platform for deploying and running machine learning models.

Creates a new serverless inference subscription on Vultr by provisioning a dedicated AI inference endpoint, allowing you to deploy and run machine learning models via the Vultr platform.

Usage

CONSOLE

$ vultr-cli inference create [flags]

Examples

CONSOLE

# Full example
$ vultr-cli inference create --label="example-inference"

Flags

Shorthand	Long Version	Description
-l	--label	label for the new inference subscription

0 Comments

Start the conversation

Be the first to comment and share your perspective with the community.

Create | Vultr Docs