Roboflow

Platform

Platform to label data, train and deploy custom computer vision models

Price
Free tier, then paid
Access
API key

About

Computer vision platform to label images, train detection and segmentation models, and run them or ready-made models such as SAM3 and RF-DETR on a serverless GPU API. The Inference server (Apache-2.0 core) self-hosts models; the free plan keeps data and models public.

What you can do with it

  • Detect, segment and count objects in images and video with a hosted model
  • Label a dataset and train a custom object detection model
  • Run models offline on Jetson, Raspberry Pi or your own GPU servers

Get started

  1. Create a Roboflow account and copy your API key from settings
  2. Pick a model ID, such as coco/40 (RF-DETR) or your own project/version

Example

curl -F "file=@photo.jpg" \
  -H "Authorization: Bearer $ROBOFLOW_API_KEY" \
  "https://serverless.roboflow.com/coco/40?confidence=0.5"

Details

Hosting
Hosted service, Self-hosted
Available in
Worldwide
Official SDKs
Python, JavaScript/TypeScript, Swift
MCP server
Remote

Tasks

Alternatives

Other tools for the same tasks.

Last checked on .