inference package | inference repo

Roboflow Inference CLI

Roboflow Inference CLI offers a lightweight interface for running the Roboflow inference server locally or the Roboflow Hosted API.

To create custom inference server Docker images, go to the parent package, Roboflow Inference.

Roboflow has everything you need to deploy a computer vision model to a range of devices and environments. Inference supports object detection, classification, and instance segmentation models, and running foundation models (CLIP and SAM).

👩‍🏫 Examples

inference server start

Starts a local inference server. It optionally takes a port number (default is 9001) and will only start the docker container if there is not already a container running on that port.

Before you begin, ensure that you have Docker installed on your machine. Docker provides a containerized environment, allowing the Roboflow Inference Server to run in a consistent and isolated manner, regardless of the host system. If you haven't installed Docker yet, you can get it from Docker's official website.

The CLI will automatically detect the device you are running on and pull the appropriate Docker image.

inference server start --port 9001 [-e {optional_path_to_file_with_env_variables}]

Parameter --env-file (or -e) is the optional path for .env file that will be loaded into inference server in case that values of internal parameters needs to be adjusted. Any value passed explicitly as command parameter is considered as more important and will shadow the value defined in .env file under the same target variable name.

inference server status

Checks the status of the local inference server.

inference server status

inference server stop

Stops the inference server.

inference server stop

inference infer

Runs inference on a single image. It takes a path to an image, a Roboflow project name, model version, and API key, and will return a JSON object with the model's predictions. You can also specify a host to run inference on our hosted inference server.

Local image

inference infer ./image.jpg --project-id my-project --model-version 1 --api-key my-api-key

Hosted image

inference infer https://[YOUR_HOSTED_IMAGE_URL] --project-id my-project --model-version 1 --api-key my-api-key

Hosted API inference

inference infer ./image.jpg --project-id my-project --model-version 1 --api-key my-api-key --host https://serverless.roboflow.com

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.

📝 license

The Roboflow Inference code is distributed under an Apache 2.0 license. The models supported by Roboflow Inference have their own licenses. View the licenses for supported models below.

model	license
`inference/models/clip`	MIT
`inference/models/sam`	Apache 2.0
`inference/models/vit`	Apache 2.0
`inference/models/yolact`	MIT
`inference/models/yolov5`	AGPL-3.0
`inference/models/yolov7`	GPL-3.0
`inference/models/yolov8`	AGPL-3.0

🚀 enterprise

With a Roboflow Inference Enterprise License, you can access additional Inference features, including:

Server cluster deployment
Active learning
YOLOv5 and YOLOv8 model sub-license

To learn more, contact the Roboflow team.

📚 documentation

Visit our documentation for usage examples and reference for Roboflow Inference.

💻 explore more Roboflow open source projects

Project	Description
supervision	General-purpose utilities for use in computer vision projects, from predictions filtering and display to object tracking to model evaluation.
Autodistill	Automatically label images for use in training computer vision models.
Inference (this project)	An easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.
Notebooks	Tutorials for computer vision tasks, from training state-of-the-art models to tracking objects to counting objects in a zone.
Collect	Automated, intelligent data collection powered by CLIP.

Release files for inference-cli 1.4.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for inference-cli 1.4.1
File	Interpreter	ABI	Platform	Reset
inference_cli-1.4.1-py3-none-any.whl 207.2 kB Aug 14, 2026	Python 3	none	any	Details

Release files / inference_cli-1.4.1-py3-none-any.whl

Download URL	inference_cli-1.4.1-py3-none-any.whl
Size	207.2 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`e6a57a47adaf64526fc177ae9e769c3fab6e65432924767b353367409982a2ea`
BLAKE2b-256 checksum How to use checksums	`6fb92781493e42d660dc92638e4bd61547a2965ee19fc2d00b836cb45414dc9b`
Upload date	Aug 14, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/roboflow/inference
Publishing commit: github.com/roboflow/inference/tree/a6caf5e75f76a31c6cc41eb167c01ef0a2e23f76

Workflow

Publishing configuration: github.com/roboflow/inference/blob/a6caf5e75f76a31c6cc41eb167c01ef0a2e23f76/.github/workflows/publish.pypi.yml
Publishing logs: github.com/roboflow/inference/actions/runs/31821471458/attempts/1

Artifact

Subject: inference_cli-1.4.1-py3-none-any.whl
SHA-256 checksum: e6a57a47adaf64526fc177ae9e769c3fab6e65432924767b353367409982a2ea Verifying attestations