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

# CLI

> Learn how to run inference using the command-line interface.

In this tutorial, we will teach you how to use the command-line interface to run models. We will be querying the `RedPajama-INCITE-7B-Base` model to complete the phrase "Space robots are".

For the full API reference go to [API Reference](/reference/chat).

## Pre-requisites

* Make sure you have Python installed in your CLI.
* Obtain an API key from Together to access the Inference API by [signing up](https://api.together.xyz/signin).

## Install the Library

Launch your terminal and install or update the Together CLI by executing the following command:

<CodeGroup>
  ```shell Shell theme={null}
  pip install --upgrade together
  ```
</CodeGroup>

## Authenticate

The API Key can be configured by setting the `TOGETHER_API_KEY` environment variable, like this:

<CodeGroup>
  ```shell Shell theme={null}
  export TOGETHER_API_KEY=xxxxx
  ```
</CodeGroup>

Find your API token in your [account settings](https://api.together.xyz/settings/api-keys).

## Query a chat model

Query a chat model by running the following command.

<CodeGroup>
  ```bash Bash theme={null}
  together chat.completions \
    --message "system" "You are a helpful assistant named Together" \
    --message "user" "What is your name?" \
    --model mistralai/Mixtral-8x7B-Instruct-v0.1
  ```
</CodeGroup>

The Chat Completions CLI enables streaming tokens to stdout by default. To disable streaming, use `--no-stream`.

## Query a language or code model

To run a completion for a language or code model, use the `completions` method in the CLI.

<CodeGroup>
  ```bash Bash theme={null}
  together completions \
    "Large language models are " \
    --model mistralai/Mixtral-8x7B-v0.1 \
    --max-tokens 512 \
    --stop "."
  ```
</CodeGroup>

The Completions CLI enables streaming tokens to stdout by default. To disable streaming, use `--no-stream`.

## Query an image model

To query an image model, use the `images` method in the CLI.

<CodeGroup>
  ```bash Bash theme={null}
  together images generate \
    "space robots" \
    --model stabilityai/stable-diffusion-xl-base-1.0 \
    --n 4
  ```
</CodeGroup>

The image is opened in the default image viewer by default. To disable this, use `--no-show`.

## List all models

To list all the available models, run the following:

<CodeGroup>
  ```bash Bash theme={null}
  # Help
  together models --help

  # List models
  together models list
  ```
</CodeGroup>