Roboflow logo

RF-DETR

RF-DETRv1.4Current
byRoboflowRoboflow(saas)
Released March 19, 2025
Context1 tokens
Price (In / Out)Free / Free
CategoryVision Model
Max Output1 tokens

About RF-DETR

RF-DETR is Roboflow’s real-time transformer model family for object detection, instance segmentation, and preview keypoint detection. The source README reports Microsoft COCO and RF100-VL benchmarks and public Apache-licensed model variants.

Capabilities

object detectioninstance segmentationkeypoint detectionvisionfine tuning

Input Modalities

image

Output Modalities

bounding-boxesmaskskeypoints

Technical Details

API Identifier
https://github.com/roboflow/rf-detr
Category
Vision Model
Context Window
1 tokens
Max Output Tokens
1 tokens

Tags

computer-visionobject-detectionsegmentationopen-sourceroboflowgithubfine-tuning

Benchmarks

Performance scores for RF-DETR across standard benchmarks.

COCO AP50:95 Object DetectionRoboflow RF-DETR README benchmark table · Jun 2026
60.1%
RF100-VL AP50:95 Object DetectionRoboflow RF-DETR README benchmark table · Jun 2026
63.2%
COCO Keypoint AP50:95Roboflow RF-DETR README benchmark table · Jun 2026
71.8%

Pricing

Token pricing for RF-DETR API usage.

Input Tokens

Free

per million tokens

Output Tokens

Free

per million tokens

Pricing Calculator

Input cost$0.00
Output cost$0.00
Estimated monthly cost$0.00

Open-source model package and public weights are listed in the source repository. There is no verified hosted token API price for this model page; operating cost depends on local GPU or inference infrastructure. Context and max output fields are schema placeholders because RF-DETR is a vision detection model, not a token LLM.

Competing Models

Same pricing tier — direct alternatives to RF-DETR

specialty
Roboflow logo

Computer vision tools for developers and enterprises

Founded 2019United States
View full profile