open-interpreter/docs/usage/terminal/arguments.mdx

---
title: Arguments
---

**[Modes](/docs/usage/terminal/arguments#modes)**

`--vision`, `--os`.

**[Model Settings](/docs/usage/terminal/arguments#model-settings)**

`--model`, `--fast`, `--local`, `--temperature`, `--context_window`, `--max_tokens`, `--max_output`, `--api_base`, `--api_key`, `--api_version`, `--llm_supports_functions`, `--llm_supports_vision`.

**[Configuration](/docs/usage/terminal/arguments#Configuration)**

`--profiles`, `--profile`, `--custom_instructions`, `--system_message`.

**[Options](/docs/usage/terminal/arguments#options)**

`--safe_mode`, `--auto_run`, `--force_task_completion`, `--verbose`, `--max_budget`, `--speak_messages`, `--multi_line`.

**[Other](/docs/usage/terminal/arguments#other)**

`--version`, `--help`.

---

## Modes

#### `--vision` or `-vi`

Enables vision mode for multimodal models. Defaults to GPT-4-turbo.

<CodeGroup>
```bash Terminal
interpreter --vision
```

```yaml Config
vision: true
```

</CodeGroup>

#### `--os` or `-o`

Enables OS mode for multimodal models. Defaults to GPT-4-turbo.

<CodeGroup>
    
    ```bash Terminal
    interpreter --os
    ```

    ```yaml Config
    os: true
    ```

</CodeGroup>

---

## Model Settings

#### `--model` or `-m`

Specifies which language model to use. Check out the [models](https://docs.openinterpreter.com/language-model-setup/introduction) section for a list of available models.

<CodeGroup>
    
```bash Terminal
interpreter --model "gpt-3.5-turbo"
```

```yaml Config
model: gpt-3.5-turbo
```

</CodeGroup>

#### `--fast` or `-f`

Sets the model to gpt-3.5-turbo.

<CodeGroup>
```bash Terminal
interpreter --fast
```

```yaml Config
fast: true
```

</CodeGroup>

#### `--local` or `-l`

Run the model locally. Check the [models page](/language-model-setup/introduction) for more information.

<CodeGroup>

```bash Terminal
interpreter --local
```

```yaml Config
local: true
```

</CodeGroup>

#### `--temperature` or `-t`

Sets the randomness level of the model's output.

<CodeGroup>
    
```bash Terminal
interpreter --temperature 0.7
```

```yaml Config
temperature: 0.7
```

</CodeGroup>

#### `--context_window` or `-c`

Manually set the context window size in tokens for the model.

<CodeGroup>

```bash Terminal
interpreter --context_window 16000
```

```yaml Config
context_window: 16000
```

</CodeGroup>

#### `--max_tokens` or `-x`

Sets the maximum number of tokens that the model can generate in a single response.

<CodeGroup>

```bash Terminal
interpreter --max_tokens 100
```

```yaml Config
max_tokens: 100
```

</CodeGroup>

#### `--max_output` or `-xo`

Set the maximum number of characters for code outputs.

<CodeGroup>
```bash Terminal
interpreter --max_output 1000
```

```yaml Config
max_output: 1000
```

</CodeGroup>
#### `--api_base` or `-ab`

If you are using a custom API, specify its base URL with this argument.

<CodeGroup>

```bash Terminal
interpreter --api_base "https://api.example.com"
```

```yaml Config
api_base: https://api.example.com
```

</CodeGroup>

#### `--api_key` or `-ak`

Set your API key for authentication when making API calls.

<CodeGroup>

```bash Terminal
interpreter --api_key "your_api_key_here"
```

```yaml Config
api_key: your_api_key_here
```

</CodeGroup>

#### `--api_version` or `-av`

Optionally set the API version to use with your selected model. (This will override environment variables)

<CodeGroup>
```bash Terminal
interpreter --api_version 2.0.2
```

```yaml Config
api_version: 2.0.2
```

</CodeGroup>
#### `--llm_supports_functions` or `-lsf`

Inform Open Interpreter that the language model you're using supports function calling.

<CodeGroup>
```bash Terminal
interpreter --llm_supports_functions
```

```yaml Config
llm_supports_functions: true
```

</CodeGroup>
#### `--no-llm_supports_functions`

Inform Open Interpreter that the language model you're using does not support function calling.

<CodeGroup>
  ```bash Terminal interpreter --no-llm_supports_functions ```
</CodeGroup>

#### `--llm_supports_vision` or `-lsv`

Inform Open Interpreter that the language model you're using supports vision.

<CodeGroup>
```bash Terminal
interpreter --llm_supports_vision
```

```yaml Config
llm_supports_vision: true
```

</CodeGroup>

---

## Configuration

#### `--profiles`

Opens the directory containing all profiles. They can be edited in your default editor.

<CodeGroup>
```bash Terminal
interpreter --profilees
```

</CodeGroup>

#### `--profile` or `-p`

Optionally set a profile to use.

<CodeGroup>
```bash Terminal
interpreter --profile "default.yaml"
```

</CodeGroup>

#### `--custom_instructions` or `-ci`

Appends custom instructions to the system message. This is useful for adding information about the your system, preferred languages, etc.

<CodeGroup>
```bash Terminal
interpreter --custom_instructions "This is a custom instruction."
```

```yaml Config
custom_instructions: "This is a custom instruction."
```

</CodeGroup>

#### `--system_message` or `-s`

We don't recommend modifying the system message, as doing so opts you out of future updates to the system message. Use `--custom_instructions` instead, to add relevant information to the system message. If you must modify the system message, you can do so by using this argument, or by opening the profile using `--profiles`.

<CodeGroup>
```bash Terminal
interpreter --system_message "You are Open Interpreter..."
```

```yaml Config
system_message: "You are Open Interpreter..."
```

## Options

#### `--safe_mode`

Enable or disable experimental safety mechanisms like code scanning. Valid options are `off`, `ask`, and `auto`.

<CodeGroup>

```bash Terminal
interpreter --safe_mode ask
```

```yaml Config
safe_mode: ask
```

</CodeGroup>

#### `--auto_run` or `-y`

Automatically run the interpreter without requiring user confirmation.

<CodeGroup>

```bash Terminal
interpreter --auto_run
```

```yaml Config
auto_run: true
```

</CodeGroup>

#### `--force_task_completion` or `-fc`

Runs Open Interpreter in a loop, requiring it to admit to completing or failing every task.

<CodeGroup>
```bash Terminal
interpreter --force_task_completion
```

```yaml Config
force_task_completion: true
```

</CodeGroup>

#### `--verbose` or `-v`

Run the interpreter in verbose mode. Debug information will be printed at each step to help diagnose issues.

<CodeGroup>

```bash Terminal
interpreter --verbose
```

```yaml Config
verbose: true
```

</CodeGroup>

#### `--max_budget` or `-b`

Sets the maximum budget limit for the session in USD.

<CodeGroup>

```bash Terminal
interpreter --max_budget 0.01
```

```yaml Config
max_budget: 0.01
```

</CodeGroup>

#### `--speak_messages` or `-sm`

(Mac Only) Speak messages out loud using the system's text-to-speech engine.

<CodeGroup>
```bash Terminal
interpreter --speak_messages
```

```yaml Config
speak_messages: true
```

</CodeGroup>

#### `--multi_line` or `-ml`

Enable multi-line inputs starting and ending with ` ``` `

<CodeGroup>
```bash Terminal
interpreter --multi_line
```

```yaml Config
multi_line: true
```

</CodeGroup>

---

## Other

#### `--version`

Get the current installed version number of Open Interpreter.

<CodeGroup>```bash Terminal interpreter --version ```</CodeGroup>

#### `--help` or `-h`

Display all available terminal arguments.

<CodeGroup>
```bash Terminal
interpreter --help
```

</CodeGroup>