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

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

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"
}