> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/reference/inference/inference-cli.md).

# Inference CLI

The Roboflow Inference CLI is a command-line interface for the `inference` ecosystem. Use it to:

* run and manage the [Inference Server](/reference/inference/inference-cli/server.md) locally
* process data with [Workflows](/reference/inference/inference-cli/workflows.md)
* [benchmark](/reference/inference/inference-cli/benchmark.md) inference performance
* make [predictions](/reference/inference/inference-cli/infer.md) from your models
* deploy the Inference Server to the [cloud](/reference/inference/inference-cli/cloud.md)

## Installation

```bash
pip install inference-cli
```

If you have installed the `inference` Python package, the CLI is already included.

{% hint style="info" %}
This is the Inference CLI (`inference ...`), which manages the open source Inference Server. It is a different tool from the [Roboflow CLI](/reference/platform/cli.md) (`roboflow ...`), which manages platform resources such as projects, datasets, and versions.
{% endhint %}

## Supported devices

The Inference CLI currently supports the following device targets:

* x86 CPU
* ARM64 CPU
* NVIDIA GPU (including Jetson)

For Jetson-specific Inference Server images, see the [Inference Server](https://docs.roboflow.com/deployment/self-hosted/inference-server) page or pull the images directly.

## Commands

| Command                                                                  | Description                                                       |
| ------------------------------------------------------------------------ | ----------------------------------------------------------------- |
| [`inference server`](/reference/inference/inference-cli/server.md)       | Start, stop, and check the local Inference Server.                |
| [`inference infer`](/reference/inference/inference-cli/infer.md)         | Run predictions on images, directories, and video files.          |
| [`inference workflows`](/reference/inference/inference-cli/workflows.md) | Process images and videos with a Workflow.                        |
| [`inference benchmark`](/reference/inference/inference-cli/benchmark.md) | Benchmark the Inference Server or the `inference` Python package. |
| [`inference cloud`](/reference/inference/inference-cli/cloud.md)         | Deploy the Inference Server to AWS or GCP virtual machines.       |