Object Detection Model¶
v3¶
Class: RoboflowObjectDetectionModelBlockV3 (there are multiple versions of this block)
Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning
Run inference on a object-detection model hosted on or uploaded to Roboflow.
You can query any model that is private to your account, or any public model available on Roboflow Universe.
You will need to set your Roboflow API key in your Inference environment to use this block. To learn more about setting your Roboflow API key, refer to the Inference documentation.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/roboflow_object_detection_model@v3to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
model_id |
str |
Roboflow model identifier.. | ✅ |
confidence_mode |
str |
How confidence thresholds are determined.. | ✅ |
custom_confidence |
float |
Custom confidence threshold for predictions.. | ✅ |
class_filter |
List[str] |
List of accepted classes. Classes must exist in the model's training set.. | ✅ |
iou_threshold |
float |
Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more.. | ✅ |
max_detections |
int |
Maximum number of detections to return.. | ✅ |
class_agnostic_nms |
bool |
Boolean flag to specify if NMS is to be used in class-agnostic mode.. | ✅ |
max_candidates |
int |
Maximum number of candidates as NMS input to be taken into account.. | ✅ |
disable_active_learning |
bool |
Boolean flag to disable project-level active learning for this block.. | ✅ |
active_learning_target_dataset |
str |
Target dataset for active learning, if enabled.. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Object Detection Model in version v3.
- inputs:
Crop Visualization,Image Slicer,Detection Event Log,Roboflow Dataset Upload,Instance Segmentation Model,Google Gemini,Classification Label Visualization,Dynamic Crop,Image Slicer,Absolute Static Crop,Template Matching,Current Time,Pixel Color Count,Roboflow Custom Metadata,Multi-Label Classification Model,SIFT Comparison,Morphological Transformation,Background Subtraction,Line Counter Visualization,Ellipse Visualization,OpenAI,Multi-Label Classification Model,MoonshotAI Kimi,Grid Visualization,PLC ModbusTCP,Bounding Box Visualization,Morphological Transformation,Semantic Segmentation Model,Google Gemma,Object Detection Model,Cosmos 3,Motion Detection,OpenAI,Multi-Label Classification Model,Webhook Sink,VLM As Detector,Size Measurement,Depth Estimation,Image Preprocessing,OPC UA Writer Sink,Single-Label Classification Model,Line Counter,Stitch Images,Roboflow Dataset Upload,OpenAI,Camera Calibration,Google Vision OCR,OpenAI,QR Code Generator,Florence-2 Model,Polygon Zone Visualization,Contrast Equalization,VLM As Classifier,Detections List Roll-Up,Clip Comparison,Pixelate Visualization,Qwen 3.6 API,PLC Writer,CSV Formatter,Triangle Visualization,Stability AI Image Generation,Icon Visualization,Dot Visualization,Stability AI Outpainting,Keypoint Visualization,Relative Static Crop,Anthropic Claude,PP-OCR,Anthropic Claude,Image Stack,Roboflow Visual Search Classifier,VLM As Detector,OCR Model,GeoTag Detection,PTZ Tracking (ONVIF),Qwen 3.5 API,Halo Visualization,OpenRouter,Frame Delay,Semantic Segmentation Model,Local File Sink,Text Display,Roboflow Asset Library Attributes,Image Threshold,Image Blur,LMM,Color Visualization,Corner Visualization,JSON Parser,S3 Sink,MQTT Writer,Qwen-VL,Instance Segmentation Model,Google Gemini,Stitch OCR Detections,Slack Notification,Event Writer,Detections Consensus,Identify Outliers,SIFT,Stitch OCR Detections,Auto Rotate on Edges,Google Gemini,VLM As Classifier,Instance Segmentation Model,Dimension Collapse,Twilio SMS Notification,Trace Visualization,Single-Label Classification Model,Perspective Correction,Camera Focus,EasyOCR,Google Gemma API,PLC EthernetIP,Object Detection Model,Instance Segmentation Model,MoonshotAI Kimi,Distance Measurement,Twilio SMS/MMS Notification,Blur Visualization,Polygon Visualization,Model Monitoring Inference Aggregator,Stability AI Inpainting,Image Convert Grayscale,Microsoft SQL Server Sink,Florence-2 Model,Qwen3.5-VL,Clip Comparison,Dynamic Zone,Mask Visualization,Reference Path Visualization,Email Notification,Polygon Visualization,Roboflow Visual Search,SIFT Comparison,Halo Visualization,Contrast Enhancement,Keypoint Detection Model,Llama 3.2 Vision,GLM-OCR,CogVLM,Circle Visualization,Image Contours,Camera Focus,Heatmap Visualization,Roboflow Vision Events,Line Counter,Llama 3.2 Vision,OpenAI-Compatible LLM,Label Visualization,Background Color Visualization,Keypoint Detection Model,PLC Reader,Buffer,Single-Label Classification Model,Model Comparison Visualization,Keypoint Detection Model,LMM For Classification,Object Detection Model,Email Notification,Anthropic Claude,Identify Changes - outputs:
Crop Visualization,Detection Event Log,Roboflow Dataset Upload,ByteTrack Tracker,Instance Segmentation Model,Color Visualization,Corner Visualization,Dynamic Crop,SAM 3 Interactive,Detections Transformation,Time in Zone,Per-Class Confidence Filter,Velocity,Qwen-VL,Detections Classes Replacement,Instance Segmentation Model,Overlap Analysis,Stitch OCR Detections,Roboflow Custom Metadata,Event Writer,Multi-Label Classification Model,Detections Consensus,Mask Area Measurement,Nearest Neighbor Detection Match,Stitch OCR Detections,BoT-SORT Tracker,Time in Zone,Ellipse Visualization,Multi-Label Classification Model,Instance Segmentation Model,SAM 3,Trace Visualization,Single-Label Classification Model,Segment Anything 2 Model,Perspective Correction,Bounding Box Visualization,Camera Focus,Semantic Segmentation Model,Byte Tracker,Object Detection Model,Cosmos 3,Overlap Filter,Object Detection Model,Instance Segmentation Model,Multi-Label Classification Model,OC-SORT Tracker,Distance Measurement,Webhook Sink,Path Deviation,Size Measurement,Path Deviation,Blur Visualization,Detections Stabilizer,Model Monitoring Inference Aggregator,Florence-2 Model,Qwen3.5-VL,Single-Label Classification Model,SAM 3,Line Counter,Moondream2,Roboflow Dataset Upload,SAM2 Video Tracker,Qwen3.5,Florence-2 Model,Qwen3-VL,Detection Offset,SAM3 Video Tracker,Detections List Roll-Up,SmolVLM2,Pixelate Visualization,Keypoint Detection Model,SORT Tracker,Detections Combine,GLM-OCR,Byte Tracker,Circle Visualization,Detections Stitch,Track Class Lock,Heatmap Visualization,Triangle Visualization,Roboflow Vision Events,Line Counter,Icon Visualization,Dot Visualization,Qwen2.5-VL,Byte Tracker,Label Visualization,Time in Zone,Background Color Visualization,Keypoint Detection Model,SAM 3,Single-Label Classification Model,Model Comparison Visualization,PTZ Tracking (ONVIF),Detections Merge,GeoTag Detection,Detections Filter,Keypoint Detection Model,Object Detection Model,Frame Delay,Semantic Segmentation Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Object Detection Model in version v3 has.
Bindings
-
input
images(image): The image to infer on..model_id(roboflow_model_id): Roboflow model identifier..confidence_mode(string): How confidence thresholds are determined..custom_confidence(float_zero_to_one): Custom confidence threshold for predictions..class_filter(list_of_values): List of accepted classes. Classes must exist in the model's training set..iou_threshold(float_zero_to_one): Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..max_detections(integer): Maximum number of detections to return..class_agnostic_nms(boolean): Boolean flag to specify if NMS is to be used in class-agnostic mode..max_candidates(integer): Maximum number of candidates as NMS input to be taken into account..disable_active_learning(boolean): Boolean flag to disable project-level active learning for this block..active_learning_target_dataset(roboflow_project): Target dataset for active learning, if enabled..
-
output
inference_id(inference_id): Inference identifier.predictions(object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.model_id(roboflow_model_id): Roboflow model id.
Example JSON definition of step Object Detection Model in version v3
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_object_detection_model@v3",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence_mode": "<block_does_not_provide_example>",
"custom_confidence": 0.3,
"class_filter": [
"a",
"b",
"c"
],
"iou_threshold": 0.4,
"max_detections": 300,
"class_agnostic_nms": true,
"max_candidates": 3000,
"disable_active_learning": true,
"active_learning_target_dataset": "my_project"
}
v2¶
Class: RoboflowObjectDetectionModelBlockV2 (there are multiple versions of this block)
Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning
Run inference on a object-detection model hosted on or uploaded to Roboflow.
You can query any model that is private to your account, or any public model available on Roboflow Universe.
You will need to set your Roboflow API key in your Inference environment to use this block. To learn more about setting your Roboflow API key, refer to the Inference documentation.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/roboflow_object_detection_model@v2to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
model_id |
str |
Roboflow model identifier.. | ✅ |
confidence |
float |
Confidence threshold for predictions.. | ✅ |
class_filter |
List[str] |
List of accepted classes. Classes must exist in the model's training set.. | ✅ |
iou_threshold |
float |
Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more.. | ✅ |
max_detections |
int |
Maximum number of detections to return.. | ✅ |
class_agnostic_nms |
bool |
Boolean flag to specify if NMS is to be used in class-agnostic mode.. | ✅ |
max_candidates |
int |
Maximum number of candidates as NMS input to be taken into account.. | ✅ |
disable_active_learning |
bool |
Boolean flag to disable project-level active learning for this block.. | ✅ |
active_learning_target_dataset |
str |
Target dataset for active learning, if enabled.. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Object Detection Model in version v2.
- inputs:
Crop Visualization,Image Slicer,Detection Event Log,Roboflow Dataset Upload,Instance Segmentation Model,Google Gemini,Classification Label Visualization,Dynamic Crop,Image Slicer,Absolute Static Crop,Template Matching,Pixel Color Count,Roboflow Custom Metadata,SIFT Comparison,Morphological Transformation,Background Subtraction,Line Counter Visualization,Ellipse Visualization,OpenAI,Multi-Label Classification Model,MoonshotAI Kimi,Grid Visualization,PLC ModbusTCP,Bounding Box Visualization,Morphological Transformation,Semantic Segmentation Model,Google Gemma,Object Detection Model,Motion Detection,OpenAI,Multi-Label Classification Model,Webhook Sink,VLM As Detector,Size Measurement,Depth Estimation,Image Preprocessing,OPC UA Writer Sink,Single-Label Classification Model,Stitch Images,Roboflow Dataset Upload,Camera Calibration,OpenAI,QR Code Generator,Florence-2 Model,Polygon Zone Visualization,Contrast Equalization,VLM As Classifier,Detections List Roll-Up,Clip Comparison,Pixelate Visualization,Qwen 3.6 API,PLC Writer,Triangle Visualization,Stability AI Image Generation,Icon Visualization,Dot Visualization,Stability AI Outpainting,Keypoint Visualization,Relative Static Crop,Anthropic Claude,Anthropic Claude,Image Stack,Roboflow Visual Search Classifier,VLM As Detector,GeoTag Detection,PTZ Tracking (ONVIF),Qwen 3.5 API,Halo Visualization,OpenRouter,Frame Delay,Semantic Segmentation Model,Local File Sink,Text Display,Roboflow Asset Library Attributes,Image Threshold,Image Blur,Color Visualization,Corner Visualization,JSON Parser,S3 Sink,MQTT Writer,Qwen-VL,Instance Segmentation Model,Google Gemini,Slack Notification,Event Writer,Detections Consensus,Identify Outliers,SIFT,VLM As Classifier,Auto Rotate on Edges,Google Gemini,Dimension Collapse,Twilio SMS Notification,Trace Visualization,Perspective Correction,Camera Focus,Google Gemma API,PLC EthernetIP,Object Detection Model,Instance Segmentation Model,MoonshotAI Kimi,Distance Measurement,Twilio SMS/MMS Notification,Blur Visualization,Polygon Visualization,Model Monitoring Inference Aggregator,Stability AI Inpainting,Image Convert Grayscale,Microsoft SQL Server Sink,Florence-2 Model,Clip Comparison,Dynamic Zone,Mask Visualization,Reference Path Visualization,Email Notification,Polygon Visualization,Roboflow Visual Search,SIFT Comparison,Halo Visualization,Contrast Enhancement,Keypoint Detection Model,Llama 3.2 Vision,Circle Visualization,Image Contours,Camera Focus,Heatmap Visualization,Line Counter,Roboflow Vision Events,Llama 3.2 Vision,Label Visualization,Background Color Visualization,PLC Reader,Buffer,Single-Label Classification Model,Model Comparison Visualization,Keypoint Detection Model,Line Counter,Email Notification,Anthropic Claude,Identify Changes - outputs:
Crop Visualization,Detection Event Log,Roboflow Dataset Upload,ByteTrack Tracker,Instance Segmentation Model,Color Visualization,Corner Visualization,Dynamic Crop,SAM 3 Interactive,Detections Transformation,Time in Zone,Per-Class Confidence Filter,Velocity,Qwen-VL,Detections Classes Replacement,Instance Segmentation Model,Overlap Analysis,Stitch OCR Detections,Roboflow Custom Metadata,Event Writer,Multi-Label Classification Model,Detections Consensus,Mask Area Measurement,Nearest Neighbor Detection Match,Stitch OCR Detections,BoT-SORT Tracker,Time in Zone,Ellipse Visualization,Multi-Label Classification Model,Instance Segmentation Model,SAM 3,Trace Visualization,Single-Label Classification Model,Segment Anything 2 Model,Perspective Correction,Bounding Box Visualization,Camera Focus,Semantic Segmentation Model,Byte Tracker,Object Detection Model,Cosmos 3,Overlap Filter,Object Detection Model,Instance Segmentation Model,Multi-Label Classification Model,OC-SORT Tracker,Distance Measurement,Webhook Sink,Path Deviation,Size Measurement,Path Deviation,Blur Visualization,Detections Stabilizer,Model Monitoring Inference Aggregator,Florence-2 Model,Qwen3.5-VL,Single-Label Classification Model,SAM 3,Line Counter,Moondream2,Roboflow Dataset Upload,SAM2 Video Tracker,Qwen3.5,Florence-2 Model,Qwen3-VL,Detection Offset,SAM3 Video Tracker,Detections List Roll-Up,SmolVLM2,Pixelate Visualization,Keypoint Detection Model,SORT Tracker,Detections Combine,GLM-OCR,Byte Tracker,Circle Visualization,Detections Stitch,Track Class Lock,Heatmap Visualization,Triangle Visualization,Roboflow Vision Events,Line Counter,Icon Visualization,Dot Visualization,Qwen2.5-VL,Byte Tracker,Label Visualization,Time in Zone,Background Color Visualization,Keypoint Detection Model,SAM 3,Single-Label Classification Model,Model Comparison Visualization,PTZ Tracking (ONVIF),Detections Merge,GeoTag Detection,Detections Filter,Keypoint Detection Model,Object Detection Model,Frame Delay,Semantic Segmentation Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Object Detection Model in version v2 has.
Bindings
-
input
images(image): The image to infer on..model_id(roboflow_model_id): Roboflow model identifier..confidence(float_zero_to_one): Confidence threshold for predictions..class_filter(list_of_values): List of accepted classes. Classes must exist in the model's training set..iou_threshold(float_zero_to_one): Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..max_detections(integer): Maximum number of detections to return..class_agnostic_nms(boolean): Boolean flag to specify if NMS is to be used in class-agnostic mode..max_candidates(integer): Maximum number of candidates as NMS input to be taken into account..disable_active_learning(boolean): Boolean flag to disable project-level active learning for this block..active_learning_target_dataset(roboflow_project): Target dataset for active learning, if enabled..
-
output
inference_id(inference_id): Inference identifier.predictions(object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.model_id(roboflow_model_id): Roboflow model id.
Example JSON definition of step Object Detection Model in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_object_detection_model@v2",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence": 0.3,
"class_filter": [
"a",
"b",
"c"
],
"iou_threshold": 0.4,
"max_detections": 300,
"class_agnostic_nms": true,
"max_candidates": 3000,
"disable_active_learning": true,
"active_learning_target_dataset": "my_project"
}
v1¶
Class: RoboflowObjectDetectionModelBlockV1 (there are multiple versions of this block)
Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning
Run inference on a object-detection model hosted on or uploaded to Roboflow.
You can query any model that is private to your account, or any public model available on Roboflow Universe.
You will need to set your Roboflow API key in your Inference environment to use this block. To learn more about setting your Roboflow API key, refer to the Inference documentation.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/roboflow_object_detection_model@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
model_id |
str |
Roboflow model identifier.. | ✅ |
confidence |
float |
Confidence threshold for predictions.. | ✅ |
class_filter |
List[str] |
List of accepted classes. Classes must exist in the model's training set.. | ✅ |
iou_threshold |
float |
Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more.. | ✅ |
max_detections |
int |
Maximum number of detections to return.. | ✅ |
class_agnostic_nms |
bool |
Boolean flag to specify if NMS is to be used in class-agnostic mode.. | ✅ |
max_candidates |
int |
Maximum number of candidates as NMS input to be taken into account.. | ✅ |
disable_active_learning |
bool |
Boolean flag to disable project-level active learning for this block.. | ✅ |
active_learning_target_dataset |
str |
Target dataset for active learning, if enabled.. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Object Detection Model in version v1.
- inputs:
Crop Visualization,Image Slicer,Detection Event Log,Roboflow Dataset Upload,Instance Segmentation Model,Google Gemini,Classification Label Visualization,Dynamic Crop,Image Slicer,Absolute Static Crop,Template Matching,Pixel Color Count,Roboflow Custom Metadata,SIFT Comparison,Morphological Transformation,Background Subtraction,Line Counter Visualization,Ellipse Visualization,OpenAI,Multi-Label Classification Model,MoonshotAI Kimi,Grid Visualization,PLC ModbusTCP,Bounding Box Visualization,Morphological Transformation,Semantic Segmentation Model,Google Gemma,Object Detection Model,Motion Detection,OpenAI,Multi-Label Classification Model,Webhook Sink,VLM As Detector,Size Measurement,Depth Estimation,Image Preprocessing,OPC UA Writer Sink,Single-Label Classification Model,Stitch Images,Roboflow Dataset Upload,Camera Calibration,OpenAI,QR Code Generator,Florence-2 Model,Polygon Zone Visualization,Contrast Equalization,VLM As Classifier,Detections List Roll-Up,Clip Comparison,Pixelate Visualization,Qwen 3.6 API,PLC Writer,Triangle Visualization,Stability AI Image Generation,Icon Visualization,Dot Visualization,Stability AI Outpainting,Keypoint Visualization,Relative Static Crop,Anthropic Claude,Anthropic Claude,Image Stack,Roboflow Visual Search Classifier,VLM As Detector,GeoTag Detection,PTZ Tracking (ONVIF),Qwen 3.5 API,Halo Visualization,OpenRouter,Frame Delay,Semantic Segmentation Model,Local File Sink,Text Display,Roboflow Asset Library Attributes,Image Threshold,Image Blur,Color Visualization,Corner Visualization,JSON Parser,S3 Sink,MQTT Writer,Qwen-VL,Instance Segmentation Model,Google Gemini,Slack Notification,Event Writer,Detections Consensus,Identify Outliers,SIFT,VLM As Classifier,Auto Rotate on Edges,Google Gemini,Dimension Collapse,Twilio SMS Notification,Trace Visualization,Perspective Correction,Camera Focus,Google Gemma API,PLC EthernetIP,Object Detection Model,Instance Segmentation Model,MoonshotAI Kimi,Distance Measurement,Twilio SMS/MMS Notification,Blur Visualization,Polygon Visualization,Model Monitoring Inference Aggregator,Stability AI Inpainting,Image Convert Grayscale,Microsoft SQL Server Sink,Florence-2 Model,Clip Comparison,Dynamic Zone,Mask Visualization,Reference Path Visualization,Email Notification,Polygon Visualization,Roboflow Visual Search,SIFT Comparison,Halo Visualization,Contrast Enhancement,Keypoint Detection Model,Llama 3.2 Vision,Circle Visualization,Image Contours,Camera Focus,Heatmap Visualization,Line Counter,Roboflow Vision Events,Llama 3.2 Vision,Label Visualization,Background Color Visualization,PLC Reader,Buffer,Single-Label Classification Model,Model Comparison Visualization,Keypoint Detection Model,Line Counter,Email Notification,Anthropic Claude,Identify Changes - outputs:
Crop Visualization,Detection Event Log,Roboflow Dataset Upload,Instance Segmentation Model,ByteTrack Tracker,Google Gemini,Classification Label Visualization,Dynamic Crop,SAM 3 Interactive,Detections Transformation,Time in Zone,Per-Class Confidence Filter,Velocity,Detections Classes Replacement,Overlap Analysis,Cache Get,Current Time,Pixel Color Count,Roboflow Custom Metadata,SIFT Comparison,Mask Area Measurement,Morphological Transformation,Line Counter Visualization,BoT-SORT Tracker,OpenAI,MoonshotAI Kimi,Multi-Label Classification Model,Ellipse Visualization,SAM 3,Segment Anything 2 Model,Semantic Segmentation Model,Bounding Box Visualization,Google Gemma,Morphological Transformation,Perception Encoder Embedding Model,Byte Tracker,Cosmos 3,Overlap Filter,OpenAI,Webhook Sink,Path Deviation,Size Measurement,Depth Estimation,Image Preprocessing,OPC UA Writer Sink,Detections Stabilizer,Single-Label Classification Model,SAM 3,Line Counter,Roboflow Dataset Upload,OpenAI,SAM2 Video Tracker,Google Vision OCR,OpenAI,QR Code Generator,Florence-2 Model,Polygon Zone Visualization,Contrast Equalization,Cache Set,Detection Offset,SAM3 Video Tracker,Detections List Roll-Up,Pixelate Visualization,SORT Tracker,Qwen 3.6 API,Detections Stitch,Track Class Lock,Triangle Visualization,Stability AI Image Generation,Icon Visualization,Dot Visualization,Stability AI Outpainting,Keypoint Visualization,Byte Tracker,Anthropic Claude,Anthropic Claude,Roboflow Visual Search Classifier,SAM 3,GeoTag Detection,PTZ Tracking (ONVIF),Qwen 3.5 API,Halo Visualization,OpenRouter,Frame Delay,Local File Sink,Text Display,Roboflow Asset Library Attributes,LMM,Image Threshold,Image Blur,Color Visualization,Corner Visualization,S3 Sink,MQTT Writer,Qwen-VL,Instance Segmentation Model,CLIP Embedding Model,Google Gemini,Stitch OCR Detections,Slack Notification,Event Writer,Detections Consensus,Nearest Neighbor Detection Match,Stitch OCR Detections,Google Gemini,Time in Zone,Auto Rotate on Edges,Instance Segmentation Model,Twilio SMS Notification,Trace Visualization,Perspective Correction,Seg Preview,Camera Focus,Google Gemma API,Object Detection Model,Instance Segmentation Model,OC-SORT Tracker,MoonshotAI Kimi,Distance Measurement,Twilio SMS/MMS Notification,Path Deviation,Blur Visualization,Polygon Visualization,Model Monitoring Inference Aggregator,Stability AI Inpainting,Microsoft SQL Server Sink,Florence-2 Model,Qwen3.5-VL,Moondream2,Clip Comparison,Mask Visualization,Reference Path Visualization,Email Notification,Polygon Visualization,Roboflow Visual Search,Detections Filter,Halo Visualization,Llama 3.2 Vision,Detections Combine,GLM-OCR,CogVLM,Circle Visualization,Byte Tracker,Heatmap Visualization,Roboflow Vision Events,Line Counter,Llama 3.2 Vision,YOLO-World Model,OpenAI-Compatible LLM,Label Visualization,Time in Zone,Background Color Visualization,Model Comparison Visualization,Keypoint Detection Model,Detections Merge,LMM For Classification,Email Notification,Anthropic Claude
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Object Detection Model in version v1 has.
Bindings
-
input
images(image): The image to infer on..model_id(roboflow_model_id): Roboflow model identifier..confidence(float_zero_to_one): Confidence threshold for predictions..class_filter(list_of_values): List of accepted classes. Classes must exist in the model's training set..iou_threshold(float_zero_to_one): Minimum overlap threshold between boxes to combine them into a single detection, used in NMS. Learn more..max_detections(integer): Maximum number of detections to return..class_agnostic_nms(boolean): Boolean flag to specify if NMS is to be used in class-agnostic mode..max_candidates(integer): Maximum number of candidates as NMS input to be taken into account..disable_active_learning(boolean): Boolean flag to disable project-level active learning for this block..active_learning_target_dataset(roboflow_project): Target dataset for active learning, if enabled..
-
output
inference_id(string): String value.predictions(object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.
Example JSON definition of step Object Detection Model in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/roboflow_object_detection_model@v1",
"images": "$inputs.image",
"model_id": "my_project/3",
"confidence": 0.3,
"class_filter": [
"a",
"b",
"c"
],
"iou_threshold": 0.4,
"max_detections": 300,
"class_agnostic_nms": true,
"max_candidates": 3000,
"disable_active_learning": true,
"active_learning_target_dataset": "my_project"
}