CLI quickstart

The ant CLI provides access to the Claude API from your terminal. Every API resource is exposed as a subcommand, with output formatting, response filtering, and support for YAML or JSON file input that make it practical for both interactive exploration and automation.

Compared to calling the API with curl, ant lets you build request bodies from typed flags or piped YAML rather than hand-written JSON, inline file contents into string fields with an @path reference, and extract fields from the response with a built-in --transform query (no separate JSON tooling required). List endpoints paginate automatically. Claude Code has native support for ant.

Installation

Check the installation:

ant --version

Authentication

ant auth login opens a browser-based OAuth flow against the Claude Console and stores the resulting credentials locally, so you can call the API without creating or managing an API key.

ant auth login

Send your first request

With the binary installed and authenticated, call the Messages API:

ant messages create \
  --model claude-opus-4-8 \
  --max-tokens 1024 \
  --message '{role: user, content: "Hello, Claude"}'

{
  "model": "claude-opus-4-8",
  "id": "msg_01YMmR5XodC5nTqMxLZMKaq6",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "Hello! How are you doing today? Is there something I can help you with?"
    }
  ],
  "stop_reason": "end_turn",
  "usage": { "input_tokens": 27, "output_tokens": 20 /*, ... */ }
}

The response is the full API object, pretty-printed because stdout is a terminal.

Shell completion

The CLI ships completion scripts for bash, zsh, fish, and PowerShell. Generate and install one for your shell:

Next steps

• CLI authentication options: API keys, headless hosts, multiple workspaces, and named profiles
• Using the CLI: command structure, output formats, GJSON transforms, and request bodies
• CLI scripting and automation: version-control API resources, scripting patterns, and use from Claude Code