Deployment

22 May 2026 • 6 min read

Gemini 3.5 Flash for Vision: Evaluation and Benchmarks

SUMMARY Gemini 3.5 Flash, released at Google I/O on May 19, 2026, currently tops the Roboflow Vision Evals leaderboard across 67 real vision prompts covering defect detection, document understanding, object counting, and spatial reasoning. It outperforms Gemini 3.1 Pro on counting and spatial tasks while running roughly

21 May 2026 • 5 min read

Integrate Roboflow with OPC UA

SUMMARY The Roboflow OPC UA Writer Sink block (available on Enterprise plans) lets a Roboflow Workflow push detection results directly to an OPC UA server as live tags, making computer vision outputs visible in SCADA platforms, PLCs, and dashboards alongside other plant sensor data. This guide walks through starting the

20 May 2026 • 4 min read

Roboflow MCP: Build Vision Apps with Claude, Codex, and More

The new Roboflow MCP Server connects Claude, Codex, and other AI agents to Roboflow so they can label visual data, train custom models, and build deployable vision pipelines.

20 May 2026 • 3 min read

Launch: 300+ OpenRouter models available in Roboflow

SUMMARY Roboflow's OpenRouter integration adds a single Workflow block that routes to any of 300+ VLMs, including every major commercial model and a broad selection of open-source options, without requiring separate auth, request adapters, or retry logic for each provider. Practical patterns this enables inside Roboflow Workflows

13 May 2026 • 5 min read

GPT-5.5: Vision Benchmarks & Use Cases

Explore OpenAI GPT 5.5 vision benchmarks. Learn how its new high-resolution encoder improves document parsing and how to use it in Roboflow Workflows.

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.

16 Apr 2026 • 5 min read

Serverless GPU Inference Cost Comparison: Roboflow, GCP, AWS, Azure

SUMMARY Serving a custom RF-DETR XL model on serverless GPU infrastructure produces dramatically different monthly costs depending on the provider and traffic pattern, so this post benchmarks Roboflow Serverless, GCP Cloud Run, AWS SageMaker, and Azure Serverless GPU across three workloads: continuous inference at one request per 10 seconds,

26 Mar 2026 • 18 min read

How to Use Roboflow for Video-Heavy Pipelines

Learn to build high-throughput video pipelines with ByteTrack, Time-in-Zone logic, and Roboflow Workflows for cloud or edge.

19 Mar 2026 • 14 min read

How to Deploy Computer Vision

In this definitive guide, we break down the decisions required to build a production-grade vision system.

2 Mar 2026 • 6 min read

Inference as a Service: How Roboflow Makes Vision AI Production-Ready

This guide explores how to abstract away the complexities of GPU orchestration and hardware allocation. Roboflow offers a production-grade API with built-in active learning, model chaining, and auto-scaling to turn your vision models into real-world solutions.

3 Feb 2026 • 5 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.

22 Dec 2025 • 4 min read

AI for Live Video: Introducing the Serverless Streaming API

SUMMARY The Roboflow Serverless Video Streaming API lets you run computer vision workflows on live video from webcams, RTSP feeds, or video files by streaming directly to the cloud over WebRTC, with no inference environment to configure or manage. Compute instances are ephemeral and scale automatically, so you pay only

9 Dec 2025 • 4 min read

Introducing Roboflow Rapid: Text prompt to vision model in minutes

SUMMARY Roboflow Rapid is a prompt-based model creation engine that takes you from a text description and a handful of images or a short video to a deployed custom model without manual labeling. You type a prompt describing what to detect, Rapid automatically finds and annotates matching objects, and

8 Aug 2025 • 5 min read

How to use YOLOE for Zero-Shot Object Detection & Segmentation

SUMMARY YOLOE extends the YOLO family with zero-shot object detection and instance segmentation, letting you specify target classes at inference time rather than training a dedicated model for each task. This tutorial walks through environment setup on a Colab T4 GPU, pulling YOLOE weights from Hugging Face, running text-

25 Jul 2025 • 9 min read

How to Build an iOS App with Visual AI Capabilities

SUMMARY This tutorial walks through building an iOS app that detects glasses in real time using a custom RF-DETR Nano model trained in Roboflow and deployed via the roboflow-swift SDK. RF-DETR Nano is chosen specifically for its low latency on live camera streams, making it well suited

3 Jul 2025 • 21 min read

How to Control a PTZ Camera with Computer Vision and Roboflow Workflows

Learn how to control a PTZ camera in a computer vision application.

26 Jun 2025 • 5 min read

How to Use Perception Encoder

Learn how to use and deploy Meta AI's Perception Encoder model with Roboflow Inference.

26 Jun 2025 • 6 min read

How to Deploy RF-DETR to an NVIDIA Jetson

Learn how to deploy RF-DETR to a Roboflow Jetson.

24 Jun 2025 • 9 min read

Launch: Roboflow Instant Models

Roboflow Instant is a free, quick-to-train, few-shot model that requires as few as a half-dozen labelled images to produce an accurate object detection model.

12 Jun 2025 • 4 min read

Launch: Manage Computer Vision Deployments with Device Manager

Learn how to use the Roboflow Device Manager to manage computer vision deployments.

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.

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.

27 Feb 2025 • 5 min read

What Is Edge AI And How Does It Work?

By running models "at the edge," companies can benefit from high performance, fast decision making, reduced cloud costs, and enhanced security.

2 Jan 2025 • 6 min read

Rock, Paper, Scissors with AI: How to Make Multiplayer Games

SUMMARY HandLand is an open-source template for building two-player, gesture-controlled games in the browser using computer vision models from Roboflow Universe. The repo ships three complete games, including Rock Paper Scissors and a standoff game called 007, using WebRTC for peer video and native WebSockets for real-