Roboflow Vision Models

Compare both Roboflow vision models we track, all of them open-weight. Try them on your own images, free in the Roboflow Playground.

2 models · 2 open-weight · 2 free to try · Updated Oct 2025

About Roboflow Vision Models

Every Roboflow vision model in our catalog is open-weight. Both publish downloadable weights, so you can self-host under their own licenses instead of paying per request. The open-weight side runs on Apache 2.0 terms. The newest additions are RF-DETR Segmentation (Oct 2025) and RF-DETR (Mar 2025).

The Roboflow models we list cover instance segmentation (1 model) and object detection (1).

On the open-weight tier, RF-DETR Segmentation is the largest at 33.6M-38.6M parameters and RF-DETR the smallest at 30.5M-126.9M, small enough to run on a single GPU or on-device. Both carry a permissive license, so commercial use is straightforward.

With every model here open-weight, the real trade is size against generality: the smaller checkpoints fine-tune and deploy cheaply on your own hardware, while the larger ones cover more ground out of the box. Both Roboflow vision models run live in the Roboflow Playground, so you can run the same image through both and compare the answers before committing to one.

Which Roboflow Model Should You Use?

What each of the 2 Roboflow vision models in our catalog is built for, and how you run it.

RF-DETR Segmentation: Best for: Instance Segmentation. Open weights: Apache 2.0 license, 33.6M-38.6M parameters. Self-host it or run it here. Small enough for on-device and edge deployment. Runnable in the Playground.
RF-DETR: Best for: Object Detection. Open weights: Apache 2.0 license, 30.5M-126.9M parameters. Self-host it or run it here. Small enough for on-device and edge deployment. Runnable in the Playground.

Open-Source Roboflow Models

2 models with downloadable weights you can self-host under their licenses (Apache 2.0). All run live in the Playground through hosted APIs, so self-hosting is optional.

RF-DETR Segmentation

RF-DETR Segmentation is a real-time instance segmentation model developed by Roboflow, with a preview base model released in October 2025 under the Apache 2.0 license and the full variant family — Nano through 2XL — released in January 2026. It extends the RF-DETR object detection architecture with a segmentation head inspired by MaskDINO, enabling pixel-level object delineation while maintaining the real-time performance characteristics of the base model. It is deployable through Roboflow Inference and the open-source rfdetr Python package.RF-DETR Segmentation supports fine-tuning on custom COCO- or YOLO-format instance segmentation datasets and is benchmarked on Microsoft COCO. It is suited for applications requiring both precise object masks and real-time inference, such as robotic manipulation, quality control, and augmented reality overlays.

RF-DETR

RF-DETR is a real-time transformer-based object detection model developed by Roboflow, with code and weights first released in March 2025 under the Apache 2.0 license. It is the first real-time model to exceed 60 AP on the Microsoft COCO benchmark, built on a DINOv2 vision transformer backbone with weight-sharing neural architecture search used to identify accuracy-latency trade-offs. The full family spans six sizes from Nano (30.5M parameters, 384×384 input) to 2XL (126.9M parameters, 880×880 input), with the accompanying research paper accepted to ICLR 2026.RF-DETR is designed for strong domain adaptability, achieving state-of-the-art performance on RF100-VL, a benchmark measuring generalization to real-world object detection tasks across diverse domains. It is deployable through Roboflow Inference and supports fine-tuning on custom datasets, making it well suited for domain-specific applications with limited training data.

Frequently Asked Questions About Roboflow Vision Models

Which Roboflow models can do instance segmentation?

1 of the 2 Roboflow vision models we track handles instance segmentation: RF-DETR Segmentation. Each model page lists its full task coverage, license, and specs.

Which Roboflow models can do object detection?

1 of the 2 Roboflow vision models we track handles object detection: RF-DETR. Each model page lists its full task coverage, license, and specs.

Are Roboflow vision models open source?

Yes. Both Roboflow vision models we track publish downloadable weights you can self-host under their licenses (Apache 2.0).

How many Roboflow vision models are on Roboflow Playground?

We track 2 live Roboflow vision models. The most recent addition is RF-DETR Segmentation, released Oct 2025.

Can I try Roboflow vision models for free?

Yes. Both Roboflow models run live in the Roboflow Playground. Upload your own image, run several models on it at once, and compare the outputs side by side. No setup and no account required.

This page lists both Roboflow vision models in the Roboflow Playground catalog, all of them open-weight and free to self-host. They cover instance segmentation and object detection, among other tasks. All of them run live in the Roboflow Playground on your own images. Compare licenses, parameters, prices, and release dates side by side, or open any model page for full details.