Single-Label Classification Model

v2

Class: RoboflowClassificationModelBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.multi_class_classification.v2.RoboflowClassificationModelBlockV2

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 multi-class classification 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_classification_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..	✅
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 Single-Label Classification Model in version v2.

• inputs: Image Contours, Triangle Visualization, VLM as Classifier, SIFT Comparison, Background Color Visualization, VLM as Detector, Dynamic Crop, Roboflow Dataset Upload, Halo Visualization, Classification Label Visualization, Local File Sink, VLM as Classifier, Slack Notification, Keypoint Detection Model, Twilio SMS Notification, SIFT Comparison, PTZ Tracking (ONVIF).md), Crop Visualization, JSON Parser, Email Notification, VLM as Detector, Detections Consensus, Blur Visualization, Camera Calibration, Color Visualization, Ellipse Visualization, Relative Static Crop, Bounding Box Visualization, Webhook Sink, Identify Outliers, Grid Visualization, Instance Segmentation Model, Model Comparison Visualization, Corner Visualization, Camera Focus, Stitch Images, Pixelate Visualization, Dynamic Zone, Image Slicer, Line Counter Visualization, Model Monitoring Inference Aggregator, Reference Path Visualization, Roboflow Custom Metadata, Multi-Label Classification Model, Object Detection Model, Image Slicer, Mask Visualization, Label Visualization, Stability AI Image Generation, SIFT, Image Convert Grayscale, Stability AI Outpainting, Image Threshold, Single-Label Classification Model, Polygon Zone Visualization, Stability AI Inpainting, Identify Changes, Perspective Correction, Trace Visualization, Image Preprocessing, Roboflow Dataset Upload, Absolute Static Crop, Circle Visualization, Clip Comparison, Dot Visualization, Depth Estimation, Keypoint Visualization, Polygon Visualization, Image Blur
• outputs: Instance Segmentation Model, Detections Classes Replacement, Roboflow Dataset Upload, Classification Label Visualization, Multi-Label Classification Model, Roboflow Custom Metadata, Keypoint Detection Model, Webhook Sink, Keypoint Detection Model, Multi-Label Classification Model, Object Detection Model, Model Monitoring Inference Aggregator, Moondream2, Single-Label Classification Model, Single-Label Classification Model, Instance Segmentation Model, Roboflow Dataset Upload, Qwen2.5-VL, Object Detection Model, SmolVLM2

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Single-Label Classification 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..
  • 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

  • predictions (classification_prediction): Predictions from classifier.
  • inference_id (inference_id): Inference identifier.
  • model_id (roboflow_model_id): Roboflow model id.

Example JSON definition of step Single-Label Classification Model in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_classification_model@v2",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}

v1

Class: RoboflowClassificationModelBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.roboflow.multi_class_classification.v1.RoboflowClassificationModelBlockV1

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 multi-class classification 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_classification_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..	✅
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 Single-Label Classification Model in version v1.

• inputs: Image Contours, Triangle Visualization, VLM as Classifier, SIFT Comparison, Background Color Visualization, VLM as Detector, Dynamic Crop, Roboflow Dataset Upload, Halo Visualization, Classification Label Visualization, Local File Sink, VLM as Classifier, Slack Notification, Keypoint Detection Model, Twilio SMS Notification, SIFT Comparison, PTZ Tracking (ONVIF).md), Crop Visualization, JSON Parser, Email Notification, VLM as Detector, Detections Consensus, Blur Visualization, Camera Calibration, Color Visualization, Ellipse Visualization, Relative Static Crop, Bounding Box Visualization, Webhook Sink, Identify Outliers, Grid Visualization, Instance Segmentation Model, Model Comparison Visualization, Corner Visualization, Camera Focus, Stitch Images, Pixelate Visualization, Dynamic Zone, Image Slicer, Line Counter Visualization, Model Monitoring Inference Aggregator, Reference Path Visualization, Roboflow Custom Metadata, Multi-Label Classification Model, Object Detection Model, Image Slicer, Mask Visualization, Label Visualization, Stability AI Image Generation, SIFT, Image Convert Grayscale, Stability AI Outpainting, Image Threshold, Single-Label Classification Model, Polygon Zone Visualization, Stability AI Inpainting, Identify Changes, Perspective Correction, Trace Visualization, Image Preprocessing, Roboflow Dataset Upload, Absolute Static Crop, Circle Visualization, Clip Comparison, Dot Visualization, Depth Estimation, Keypoint Visualization, Polygon Visualization, Image Blur
• outputs: Triangle Visualization, Detections Classes Replacement, Local File Sink, Slack Notification, Twilio SMS Notification, Google Vision OCR, SIFT Comparison, Line Counter, Email Notification, OpenAI, Instance Segmentation Model, Size Measurement, Ellipse Visualization, Path Deviation, Detections Stitch, Instance Segmentation Model, Model Comparison Visualization, Corner Visualization, LMM For Classification, Cache Set, Perception Encoder Embedding Model, Reference Path Visualization, Roboflow Custom Metadata, OpenAI, Mask Visualization, Model Monitoring Inference Aggregator, Label Visualization, Stability AI Outpainting, Polygon Zone Visualization, Stability AI Inpainting, Llama 3.2 Vision, Perspective Correction, Image Preprocessing, Clip Comparison, Dot Visualization, Distance Measurement, OpenAI, Keypoint Visualization, Polygon Visualization, Image Blur, Time in Zone, Florence-2 Model, CogVLM, Google Gemini, CLIP Embedding Model, Background Color Visualization, Roboflow Dataset Upload, YOLO-World Model, Dynamic Crop, Classification Label Visualization, Halo Visualization, PTZ Tracking (ONVIF).md), Crop Visualization, Anthropic Claude, Color Visualization, Segment Anything 2 Model, Line Counter, Bounding Box Visualization, Pixel Color Count, Webhook Sink, Path Deviation, Line Counter Visualization, Florence-2 Model, Stability AI Image Generation, Moondream2, Cache Get, Image Threshold, Trace Visualization, Time in Zone, Roboflow Dataset Upload, Circle Visualization, LMM

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Single-Label Classification 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..
  • 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

  • predictions (classification_prediction): Predictions from classifier.
  • inference_id (string): String value.

Example JSON definition of step Single-Label Classification Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_classification_model@v1",
    "images": "$inputs.image",
    "model_id": "my_project/3",
    "confidence": 0.3,
    "disable_active_learning": true,
    "active_learning_target_dataset": "my_project"
}