> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/janhq/jan/llms.txt
> Use this file to discover all available pages before exploring further.

# Commands Reference

> Complete reference for all Jan CLI commands and subcommands

## Top-Level Commands

### serve

Load a local model and expose it at localhost:6767/v1. Auto-detects LlamaCPP or MLX.

```bash theme={null}
jan serve [MODEL_ID] [OPTIONS]
```

See the [serve command documentation](/cli/serve) for detailed usage.

***

### launch

Start a local model, then launch an AI agent with it pre-wired (environment variables set automatically).

```bash theme={null}
jan launch [PROGRAM] [OPTIONS] [-- PROGRAM_ARGS...]
```

See the [launch command documentation](/cli/launch) for detailed usage.

***

### threads

List and inspect conversation threads saved by the Jan app.

```bash theme={null}
jan threads <SUBCOMMAND>
```

#### Subcommands

<AccordionGroup>
  <Accordion title="threads list">
    Print all threads as JSON.

    ```bash theme={null}
    jan threads list
    ```

    **Output**: JSON array of thread objects with metadata.
  </Accordion>

  <Accordion title="threads get <ID>">
    Print a single thread's metadata as JSON.

    ```bash theme={null}
    jan threads get <THREAD_ID>
    ```

    <ParamField path="id" type="string" required>
      Thread ID to retrieve
    </ParamField>

    **Output**: JSON object with thread metadata.
  </Accordion>

  <Accordion title="threads delete <ID>">
    Permanently delete a thread and all its messages.

    ```bash theme={null}
    jan threads delete <THREAD_ID>
    ```

    <ParamField path="id" type="string" required>
      Thread ID to delete
    </ParamField>

    **Output**: Confirmation JSON with deleted thread ID.
  </Accordion>

  <Accordion title="threads messages <ID>">
    Print all messages in a thread as JSON.

    ```bash theme={null}
    jan threads messages <THREAD_ID>
    ```

    <ParamField path="thread_id" type="string" required>
      Thread ID to get messages from
    </ParamField>

    **Output**: JSON array of message objects.
  </Accordion>
</AccordionGroup>

***

### models

List and load models installed in the Jan data folder.

```bash theme={null}
jan models <SUBCOMMAND>
```

#### Subcommands

<AccordionGroup>
  <Accordion title="models list">
    Print all installed models as JSON (from the Jan data folder).

    ```bash theme={null}
    jan models list [--engine <ENGINE>]
    ```

    <ParamField query="engine" type="string" default="all">
      Filter by engine: `llamacpp`, `mlx`, or `all`
    </ParamField>

    **Example Output**:

    ```json theme={null}
    [
      {
        "id": "qwen3.5-35b-a3b",
        "engine": "llamacpp",
        "name": "Qwen 3.5 35B",
        "model_path": "/Users/you/Library/Application Support/Jan/models/qwen3.5-35b-a3b/model.gguf",
        "size_bytes": 21474836480,
        "embedding": false,
        "capabilities": ["text"],
        "mmproj_path": null
      }
    ]
    ```
  </Accordion>

  <Accordion title="models load">
    Load a model and serve it — alias for the top-level `serve` command.

    ```bash theme={null}
    jan models load [MODEL_ID] [OPTIONS]
    ```

    Accepts the same options as `jan serve`. See [serve documentation](/cli/serve).
  </Accordion>

  <Accordion title="models load-mlx">
    Load an MLX model directly (macOS / Apple Silicon only).

    ```bash theme={null}
    jan models load-mlx --model-id <MODEL_ID> [OPTIONS]
    ```

    <ParamField query="model-id" type="string" required>
      Model ID as shown by `jan models list --engine mlx`
    </ParamField>

    <ParamField query="model-path" type="string">
      Path to the MLX model directory (auto-resolved from model.yml when omitted)
    </ParamField>

    <ParamField query="bin" type="string">
      Path to the mlx-server binary (auto-discovered from Jan.app when omitted)
    </ParamField>

    <ParamField query="port" type="number" default="6767">
      Port the model server listens on (0 = pick a random free port)
    </ParamField>

    <ParamField query="ctx-size" type="number" default="0">
      Context window size in tokens (0 = model default)
    </ParamField>

    <ParamField query="embedding" type="boolean" default="false">
      Treat the model as an embedding model
    </ParamField>

    <ParamField query="timeout" type="number" default="120">
      Seconds to wait for the model server to become ready
    </ParamField>

    <ParamField query="api-key" type="string" default="">
      API key required by clients (sets MLX\_API\_KEY on the server)
    </ParamField>
  </Accordion>
</AccordionGroup>

***

### app

Show app configuration and data folder location.

```bash theme={null}
jan app <SUBCOMMAND>
```

#### Subcommands

<AccordionGroup>
  <Accordion title="app data-folder">
    Print the Jan data folder path (where models, threads, and config are stored).

    ```bash theme={null}
    jan app data-folder
    ```

    **Example Output**:

    ```json theme={null}
    {
      "data_folder": "/Users/you/Library/Application Support/Jan"
    }
    ```
  </Accordion>

  <Accordion title="app config">
    Print the Jan configuration as JSON.

    ```bash theme={null}
    jan app config
    ```

    **Output**: JSON object with Jan configuration settings.
  </Accordion>
</AccordionGroup>

***

## Global Options

<ParamField query="--help" type="flag">
  Display help information for any command

  ```bash theme={null}
  jan --help
  jan serve --help
  jan launch --help
  ```
</ParamField>

<ParamField query="--version" type="flag">
  Display the Jan CLI version

  ```bash theme={null}
  jan --version
  ```
</ParamField>

<ParamField query="-v, --verbose" type="flag">
  Print full server logs (llama.cpp / mlx output) instead of the loading spinner

  Available on: `serve`, `launch`

  ```bash theme={null}
  jan serve qwen3.5-35b --verbose
  jan launch claude --model qwen3.5-35b -v
  ```
</ParamField>

***

## Examples

<CodeGroup>
  ```bash Serve a model theme={null}
  jan serve qwen3.5-35b-a3b
  ```

  ```bash Launch Claude Code theme={null}
  jan launch claude --model qwen3.5-35b-a3b
  ```

  ```bash Auto-fit context to VRAM theme={null}
  jan serve qwen3.5-35b-a3b --fit
  ```

  ```bash Run in background theme={null}
  jan serve qwen3.5-35b-a3b --detach
  ```

  ```bash List all models theme={null}
  jan models list
  ```

  ```bash List LlamaCPP models only theme={null}
  jan models list --engine llamacpp
  ```

  ```bash Get thread details theme={null}
  jan threads get abc123
  ```

  ```bash View data folder theme={null}
  jan app data-folder
  ```
</CodeGroup>

***

## Exit Codes

* `0`: Success
* `1`: Error (with error message printed to stderr)

***

## See Also

<CardGroup cols={2}>
  <Card title="Serve Command" icon="server" href="/cli/serve">
    Detailed guide for serving models
  </Card>

  <Card title="Launch Command" icon="rocket" href="/cli/launch">
    Wire AI agents to local models
  </Card>
</CardGroup>