[ Web Proxy ]
URL:
Viewing: https://docs.digitalocean.com/reference/doctl/reference/serverless-inference/ [Back]  [Original]
doctl serverless-inference | DigitalOcean Documentation

For AI agents: The documentation index is at https://docs.digitalocean.com/llms.txt. Markdown versions of pages use the same URL with index.html.md in place of the HTML page (for example, append index.html.md to the directory path instead of opening the HTML document).

doctl serverless-inference

Generated on 18 Aug 2026 from doctl version v1.167.0

Copy page as Markdown View page as Markdown

Aliases 

inference, si

Description

The subcommands of doctl inference call the serverless inference API at https://inference.do-ai.run.

Authenticate using –access-token. The value may be a model access key or a DigitalOcean personal access token with full access; all scopes must be granted for the serverless inference API to work.

Flags

Option Description
--help, -h Help for this command
Command Description
doctl doctl is a command line interface (CLI) for the DigitalOcean API.
doctl serverless-inference async-invoke Display commands for managing async model invocations
doctl serverless-inference chat-completions Display commands for creating chat completions
doctl serverless-inference embeddings Display commands for creating embedding vectors
doctl serverless-inference images Display commands for generating images
doctl serverless-inference messages Display commands for creating Anthropic-style messages
doctl serverless-inference models Display commands for listing available inference models
doctl serverless-inference responses Display commands for creating model responses

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

    In this article...

    We can't find any results for your search.

    Try using different keywords or simplifying your search terms.

    Web Proxy Viewer  |  New URL  |  Original Page