Product Updates

20 Apr 2026 • 3 min read

Vision Events: Turning Images into Insights

Transform raw model predictions into trackable insights. Vision Events provides a secure, searchable record of your model deployments alongside images and custom metadata.

10 Apr 2026 • 2 min read

Roboflow Ranked #9 AI Product in G2’s 2026 Awards

At Roboflow, our mission has always been to democratize computer vision. We believe that giving developers the tools to make the world programmable will solve some of the world’s hardest problems. Today, we are proud to share a significant milestone in that journey: After being named the #1 Image

12 Mar 2026 • 4 min read

Inference 1.0: Foundational Infrastructure for Visual Understanding

Today, Roboflow is announcing Inference 1.0, the most trusted and reliable vision AI inference engine. As vision AI has entered a period of exponential growth, the technology must evolve to continue serving the needs of the ecosystem. Processing visual data like images, videos, and real-time streams at enterprise scale

3 Feb 2026 • 4 min read

Launch: Process data directly from Wasabi, Backblaze B2, Cloudflare R2, and more

We’ve expanded Batch Processing to support the wider ecosystem of S3-compatible storage. Learn how to run inference on terabytes of data stored in Wasabi, Backblaze, and Cloudflare R2, and more.

28 Jan 2026 • 1 min read

Launch: Workflows Builder 2.0

Workflows Builder 2.0 is here with a drag-to-connect interface that makes building and understanding computer vision pipelines faster and clearer.

22 Jan 2026 • 4 min read

New RF-DETR Segmentation Checkpoints from Nano to 2XLarge

RF-DETR-Seg brings real-time instance segmentation to the same level RF-DETR already reached in object detection, with strong accuracy across a full range of model sizes from Nano to 2XLarge.

15 Jan 2026 • 4 min read

Launch: Train and Deploy YOLO26 with Roboflow

YOLO26 was released on January 14th, 2026, and we are excited to announce that the latest YOLO model is fully supported on the Roboflow platform for labeling, training, and deployment. YOLO26 is the latest evolution of real-time computer vision models. Optimized specifically for edge deployment and CPU performance, YOLO26 introduces

2 Jan 2026 • 2 min read

#Shipmas: Edge Day

We're continuing our 12 Days of Shipmas with a set of features focused on deploying to the edge. ’Twas the night before #Shipmas When all through the cloud, Not a model was training, not a pipeline was loud. The GPUs were idling, tucked under their rack, While cameras

26 Dec 2025 • 2 min read

Launch: Advanced Enterprise Security Features

The Enterprise team at Roboflow is focused on helping large organizations collaborate to build cutting-edge vision models and applications. We've released more customizable security and access features to give enterprises granular control of Roboflow. Custom Role-based Access Controls (RBAC) The default RBAC roles in Roboflow cover a lot

22 Dec 2025 • 4 min read

AI for Live Video: Introducing the Serverless Streaming API

Today we are announcing the Serverless Video Streaming API, the simplest way to run AI on live video streams. Previously, using AI to understand live video streams meant managing complex cloud infrastructure or configuring local hardware. The Serverless Video Streaming API removes those barriers, allowing you to run powerful vision

9 Dec 2025 • 4 min read

Introducing Roboflow Rapid: Text prompt to vision model in minutes

For most of computer vision's history, training has been extremely challenging. Going from an idea to a deployed application meant spending weeks labeling hundreds or thousands of images by hand just to see if a concept would work. Now the era of manual labeling is ending. Today, we

19 Nov 2025 • 5 min read

Launch: Use Segment Anything 3 (SAM 3) with Roboflow

Today, we are introducing new tools powered by Segment Anything 3 (SAM 3) that significantly change how people build computer vision applications. SAM 3 is a powerful vision foundation model that detects, segments, and tracks objects in images and videos based on prompts. See our detailed SAM 3 model overview

13 Nov 2025 • 3 min read

Roboflow Named Leader in Image Recognition Software

We’re proud to announce that as of November 2025, Roboflow has been ranked the #1 Image Recognition product on G2.

21 Aug 2025 • 2 min read

Roboflow Joins Microsoft's Pegasus Partnership Program

We are excited to announce Roboflow has joined Microsoft's Pegasus Program.  The Pegasus Program is an invite-only initiative that provides industry-leading businesses with a deep partnership across Microsoft’s go-to-market and technical teams. Roboflow is on the exclusive list of companies closely partnering with Microsoft to drive the

1 Aug 2025 • 4 min read

Launch: Verified Model Metrics

Selecting the right computer vision model for production starts with accurately measuring and comparing model performance. Evaluation metrics quantify a model’s capabilities, helping teams make informed decisions and choose models suited for real-world use. Among the many metrics available, Mean Average Precision (mAP) is a leading metric because it

24 Jul 2025 • 5 min read

Advancing State of the Art Object Detection (Again) with RF-DETR

Learn how to use and train the three new state-of-the-art RF-DETR object detection model sizes.

28 Mar 2025 • 7 min read

Launch: Train and Deploy RF-DETR Models with Roboflow

Learn how to train RF-DETR models with Roboflow Train and deploy RF-DETR models with Roboflow Workflows and Inference.

20 Mar 2025 • 8 min read

RF-DETR: A SOTA Real-Time Object Detection Model

Today we are releasing RF-DETR, a state-of-the-art real-time object detection model. Learn more about how RF-DETR works and how to use the model.

13 Mar 2025 • 7 min read

Launch: Roboflow Batch Processing

Learn how to use Batch Processing to run multi-step vision AI workflows on a folder of images or videos.

20 Feb 2025 • 5 min read

Launch: Use YOLOv12 with Roboflow

Learn how to label data for, train, and deploy YOLOv12 models with Roboflow.

19 Feb 2025 • 5 min read

Parallel Inference Requests with Roboflow

Learn how to make parallel inference requests to the Roboflow Hosted API and to a Roboflow Dedicated Deployment.

15 Jan 2025 • 3 min read

How to Deploy Computer Vision Models to a Raspberry Pi

Learn how to deploy computer vision models to a Raspberry Pi.

13 Dec 2024 • 3 min read

Launch: Dedicated Deployments

When you deploy a computer vision model, you may want to have a dedicated server, or several servers, to which you can route requests to your vision model. This is ideal for workflows where you are processing images from a client (i.e. a web application), recorded videos, and more.

10 Dec 2024 • 5 min read

Launch: Fine-Tune Florence-2 for VQA with Roboflow

Learn how to fine-tune Florence-2 for visual question answering (VQA) using Roboflow.