About CLI

Roboflow Inference CLI

Roboflow Inference CLI is command-line interface for inference ecosystem, providing an easy way to:

• run and manage inference server locally

• process data with Workflows

• benchmark inference performance

• make predictions from your models

• deploy inference server in cloud

Installation

pip install roboflow-cli

inference-cli is part of inference

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

Supported Devices

Roboflow Inference CLI currently supports the following device targets:

• x86 CPU
• ARM64 CPU
• NVIDIA GPU

For Jetson specific inference server images, check out the Roboflow Inference package, or pull the images directly following instructions in the official Roboflow Inference documentation.