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 YAML or JSON file input.

Compared to curl, ant builds request bodies from typed flags or piped YAML instead of hand-written JSON, and inlines file contents into string fields with an @path reference. It extracts response fields with a built-in --transform query, so you don't need a separate tool like jq, and it paginates list endpoints automatically.



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