camel ask

--api-key

API key. Also reads ANTHROPIC_API_KEY, OPENAI_API_KEY, WATSONX_APIKEY, or LLM_API_KEY env vars

String

--api-type

API type: 'ollama', 'openai', 'anthropic', or 'watsonx'

ApiType

--max-iterations

Maximum number of tool-calling rounds

25

int

--model

Model to use. Default: the provider’s default; with Ollama the installed model best at tool calling, such as qwen3.6

String

--name

Name or PID of the Camel process. Auto-detected when exactly one process is running

String

--show-stats

Show token usage and elapsed time after response

boolean

--show-tools

Show tool calls and results as they happen

boolean

--timeout

Timeout in seconds for LLM response

120

int

--tools

The tools the model gets: core (a small set, for a local model), full, or auto (core for a local model, full for a hosted one)

auto

ToolSet

--url

LLM API endpoint URL. Auto-detected if not specified. Also reads AZURE_OPENAI_ENDPOINT or WATSONX_URL env vars

String

--verbose

Print debug information: HTTP requests, responses, and parsed results

boolean

--yes

Run the calls that ask first without asking: file writes, messages to endpoints the integration does not have, SQL that changes data, code expressions, stopping the integration, and camel commands that change something. For scripts, where there is no terminal to ask on

boolean

-h,--help

Display the help and sub-commands

boolean