SAM 3

v3

Class: SegmentAnything3BlockV3 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.segment_anything3.v3.SegmentAnything3BlockV3

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 Segment Anything 3 (SAM3), a zero-shot instance segmentation model, on an image.

You can use text prompts for open-vocabulary segmentation - just specify class names and SAM3 will segment those objects in the image.

This block supports two output formats: - rle (default): Returns masks in RLE (Run-Length Encoding) format, which is more memory-efficient - polygons: Returns polygon coordinates for each mask

RLE format is recommended for high-resolution images or workflows with many detections.

Type identifier

Use the following identifier in step "type" field: roboflow_core/sam3@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	model version. You only need to change this for fine tuned sam3 models..	✅
class_names	Optional[List[str], str]	List of classes to recognise.	✅
confidence	float	Minimum confidence threshold for predicted masks.	✅
per_class_confidence	List[float]	List of confidence thresholds per class (must match class_names length).	✅
apply_nms	bool	Whether to apply Non-Maximum Suppression across prompts.	✅
nms_iou_threshold	float	IoU threshold for cross-prompt NMS. Must be in [0.0, 1.0].	✅
output_format	str	'rle' returns efficient RLE encoding (recommended), 'polygons' returns polygon coordinates.	❌

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 SAM 3 in version v3.

• inputs: Instance Segmentation Model, Clip Comparison, Florence-2 Model, Morphological Transformation, Google Gemini, LMM, Instance Segmentation Model, Polygon Zone Visualization, Motion Detection, Keypoint Visualization, Email Notification, Roboflow Custom Metadata, Camera Focus, Anthropic Claude, Multi-Label Classification Model, Image Threshold, LMM For Classification, Keypoint Detection Model, Anthropic Claude, Email Notification, Gaze Detection, Reference Path Visualization, Stitch OCR Detections, Camera Focus, Image Slicer, Stability AI Image Generation, Stability AI Outpainting, Stitch Images, Blur Visualization, OpenAI, Roboflow Dataset Upload, Depth Estimation, Google Gemini, CogVLM, Image Preprocessing, Local File Sink, Florence-2 Model, Identify Outliers, Image Convert Grayscale, JSON Parser, VLM as Detector, Dynamic Crop, Dot Visualization, Triangle Visualization, OCR Model, Cosine Similarity, Crop Visualization, PTZ Tracking (ONVIF).md), Twilio SMS Notification, Perspective Correction, Twilio SMS/MMS Notification, EasyOCR, Detections List Roll-Up, Dimension Collapse, Grid Visualization, Google Gemini, Object Detection Model, Trace Visualization, QR Code Generator, Pixelate Visualization, OpenAI, Detections Consensus, Camera Calibration, Roboflow Dataset Upload, Buffer, Webhook Sink, Single-Label Classification Model, Object Detection Model, VLM as Detector, Background Subtraction, SIFT Comparison, Bounding Box Visualization, Contrast Equalization, Halo Visualization, Model Comparison Visualization, Label Visualization, Slack Notification, Dynamic Zone, OpenAI, Circle Visualization, Image Contours, Background Color Visualization, Image Blur, Mask Visualization, VLM as Classifier, Size Measurement, Google Vision OCR, Llama 3.2 Vision, Color Visualization, Corner Visualization, Classification Label Visualization, Single-Label Classification Model, OpenAI, Clip Comparison, Line Counter Visualization, Ellipse Visualization, Icon Visualization, Model Monitoring Inference Aggregator, Image Slicer, Absolute Static Crop, VLM as Classifier, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Keypoint Detection Model, Identify Changes, Relative Static Crop, SIFT, CSV Formatter, Text Display, Multi-Label Classification Model
• outputs: Florence-2 Model, Pixelate Visualization, Detections Consensus, Roboflow Dataset Upload, Detections Stitch, Roboflow Custom Metadata, Detections Merge, Detection Offset, Bounding Box Visualization, Byte Tracker, Model Comparison Visualization, Halo Visualization, Label Visualization, Byte Tracker, Dynamic Zone, Circle Visualization, Camera Focus, Overlap Filter, Background Color Visualization, Mask Visualization, Size Measurement, Blur Visualization, Time in Zone, Color Visualization, Bounding Rectangle, Detection Event Log, Roboflow Dataset Upload, Corner Visualization, Detections Transformation, Path Deviation, Detections Combine, Segment Anything 2 Model, Detections Classes Replacement, Florence-2 Model, Time in Zone, Byte Tracker, Ellipse Visualization, Icon Visualization, Dynamic Crop, Velocity, Time in Zone, Model Monitoring Inference Aggregator, Line Counter, Detections Stabilizer, Dot Visualization, Triangle Visualization, Polygon Visualization, Stability AI Inpainting, Crop Visualization, PTZ Tracking (ONVIF).md), Path Deviation, Perspective Correction, Distance Measurement, Detections List Roll-Up, Detections Filter, Line Counter, Trace Visualization

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SAM 3 in version v3 has.

Bindings

• input

  • images (image): The image to infer on..
  • model_id (roboflow_model_id): model version. You only need to change this for fine tuned sam3 models..
  • class_names (Union[string, list_of_values]): List of classes to recognise.
  • confidence (float): Minimum confidence threshold for predicted masks.
  • per_class_confidence (list_of_values): List of confidence thresholds per class (must match class_names length).
  • apply_nms (boolean): Whether to apply Non-Maximum Suppression across prompts.
  • nms_iou_threshold (float): IoU threshold for cross-prompt NMS. Must be in [0.0, 1.0].

• output

  • predictions (Union[rle_instance_segmentation_prediction, instance_segmentation_prediction]): Prediction with detected bounding boxes and RLE-encoded segmentation masks in form of sv.Detections(...) object if rle_instance_segmentation_prediction or Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object if instance_segmentation_prediction.

Example JSON definition of step SAM 3 in version v3

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/sam3@v3",
    "images": "$inputs.image",
    "model_id": "sam3/sam3_final",
    "class_names": [
        "car",
        "person"
    ],
    "confidence": 0.3,
    "per_class_confidence": [
        0.3,
        0.5,
        0.7
    ],
    "apply_nms": "<block_does_not_provide_example>",
    "nms_iou_threshold": 0.5,
    "output_format": "rle"
}

v2

Class: SegmentAnything3BlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.segment_anything3.v2.SegmentAnything3BlockV2

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 Segment Anything 3, a zero-shot instance segmentation model, on an image.

You can pass in boxes/predictions from other models as prompts, or use a text prompt for open-vocabulary segmentation. If you pass in box detections from another model, the class names of the boxes will be forwarded to the predicted masks.

Type identifier

Use the following identifier in step "type" field: roboflow_core/sam3@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	model version. You only need to change this for fine tuned sam3 models..	✅
class_names	Optional[List[str], str]	List of classes to recognise.	✅
confidence	float	Minimum confidence threshold for predicted masks.	✅
per_class_confidence	List[float]	List of confidence thresholds per class (must match class_names length).	✅
apply_nms	bool	Whether to apply Non-Maximum Suppression across prompts.	✅
nms_iou_threshold	float	IoU threshold for cross-prompt NMS. Must be in [0.0, 1.0].	✅

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 SAM 3 in version v2.

• inputs: Instance Segmentation Model, Clip Comparison, Florence-2 Model, Morphological Transformation, Google Gemini, LMM, Instance Segmentation Model, Polygon Zone Visualization, Motion Detection, Keypoint Visualization, Email Notification, Roboflow Custom Metadata, Camera Focus, Anthropic Claude, Multi-Label Classification Model, Image Threshold, LMM For Classification, Keypoint Detection Model, Anthropic Claude, Email Notification, Gaze Detection, Reference Path Visualization, Stitch OCR Detections, Camera Focus, Image Slicer, Stability AI Image Generation, Stability AI Outpainting, Stitch Images, Blur Visualization, OpenAI, Roboflow Dataset Upload, Depth Estimation, Google Gemini, CogVLM, Image Preprocessing, Local File Sink, Florence-2 Model, Identify Outliers, Image Convert Grayscale, JSON Parser, VLM as Detector, Dynamic Crop, Dot Visualization, Triangle Visualization, OCR Model, Cosine Similarity, Crop Visualization, PTZ Tracking (ONVIF).md), Twilio SMS Notification, Perspective Correction, Twilio SMS/MMS Notification, EasyOCR, Detections List Roll-Up, Dimension Collapse, Grid Visualization, Google Gemini, Object Detection Model, Trace Visualization, QR Code Generator, Pixelate Visualization, OpenAI, Detections Consensus, Camera Calibration, Roboflow Dataset Upload, Buffer, Webhook Sink, Single-Label Classification Model, Object Detection Model, VLM as Detector, Background Subtraction, SIFT Comparison, Bounding Box Visualization, Contrast Equalization, Halo Visualization, Model Comparison Visualization, Label Visualization, Slack Notification, Dynamic Zone, OpenAI, Circle Visualization, Image Contours, Background Color Visualization, Image Blur, Mask Visualization, VLM as Classifier, Size Measurement, Google Vision OCR, Llama 3.2 Vision, Color Visualization, Corner Visualization, Classification Label Visualization, Single-Label Classification Model, OpenAI, Clip Comparison, Line Counter Visualization, Ellipse Visualization, Icon Visualization, Model Monitoring Inference Aggregator, Image Slicer, Absolute Static Crop, VLM as Classifier, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Keypoint Detection Model, Identify Changes, Relative Static Crop, SIFT, CSV Formatter, Text Display, Multi-Label Classification Model
• outputs: Florence-2 Model, Pixelate Visualization, Detections Consensus, Roboflow Dataset Upload, Detections Stitch, Roboflow Custom Metadata, Detections Merge, Detection Offset, Bounding Box Visualization, Byte Tracker, Model Comparison Visualization, Halo Visualization, Byte Tracker, Label Visualization, Dynamic Zone, Circle Visualization, Camera Focus, Overlap Filter, Background Color Visualization, Size Measurement, Mask Visualization, Blur Visualization, Time in Zone, Path Deviation, Bounding Rectangle, Detection Event Log, Roboflow Dataset Upload, Corner Visualization, Detections Transformation, Color Visualization, Detections Combine, Segment Anything 2 Model, Detections Classes Replacement, Florence-2 Model, Time in Zone, Ellipse Visualization, Icon Visualization, Byte Tracker, Dynamic Crop, Velocity, Line Counter, Model Monitoring Inference Aggregator, Time in Zone, Detections Stabilizer, Triangle Visualization, Dot Visualization, Polygon Visualization, Stability AI Inpainting, Crop Visualization, PTZ Tracking (ONVIF).md), Path Deviation, Perspective Correction, Distance Measurement, Detections List Roll-Up, Detections Filter, Line Counter, Trace Visualization

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SAM 3 in version v2 has.

Bindings

• input

  • images (image): The image to infer on..
  • model_id (roboflow_model_id): model version. You only need to change this for fine tuned sam3 models..
  • class_names (Union[string, list_of_values]): List of classes to recognise.
  • confidence (float): Minimum confidence threshold for predicted masks.
  • per_class_confidence (list_of_values): List of confidence thresholds per class (must match class_names length).
  • apply_nms (boolean): Whether to apply Non-Maximum Suppression across prompts.
  • nms_iou_threshold (float): IoU threshold for cross-prompt NMS. Must be in [0.0, 1.0].

• output

  • predictions (instance_segmentation_prediction): Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object.

Example JSON definition of step SAM 3 in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/sam3@v2",
    "images": "$inputs.image",
    "model_id": "sam3/sam3_final",
    "class_names": [
        "car",
        "person"
    ],
    "confidence": 0.3,
    "per_class_confidence": [
        0.3,
        0.5,
        0.7
    ],
    "apply_nms": "<block_does_not_provide_example>",
    "nms_iou_threshold": 0.5
}

v1

Class: SegmentAnything3BlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.segment_anything3.v1.SegmentAnything3BlockV1

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 Segment Anything 3, a zero-shot instance segmentation model, on an image.

You can pass in boxes/predictions from other models as prompts, or use a text prompt for open-vocabulary segmentation. If you pass in box detections from another model, the class names of the boxes will be forwarded to the predicted masks.

Type identifier

Use the following identifier in step "type" field: roboflow_core/sam3@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	model version. You only need to change this for fine tuned sam3 models..	✅
class_names	Optional[List[str], str]	List of classes to recognise.	✅
threshold	float	Threshold for predicted mask scores.	✅

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 SAM 3 in version v1.

• inputs: Instance Segmentation Model, Clip Comparison, Florence-2 Model, Morphological Transformation, Google Gemini, LMM, Instance Segmentation Model, Polygon Zone Visualization, Motion Detection, Keypoint Visualization, Email Notification, Roboflow Custom Metadata, Camera Focus, Anthropic Claude, Multi-Label Classification Model, Image Threshold, LMM For Classification, Keypoint Detection Model, Anthropic Claude, Email Notification, Gaze Detection, Reference Path Visualization, Stitch OCR Detections, Camera Focus, Image Slicer, Stability AI Image Generation, Stability AI Outpainting, Stitch Images, Blur Visualization, OpenAI, Roboflow Dataset Upload, Depth Estimation, Google Gemini, CogVLM, Image Preprocessing, Local File Sink, Florence-2 Model, Image Convert Grayscale, Dynamic Crop, Dot Visualization, Triangle Visualization, OCR Model, Cosine Similarity, Crop Visualization, Twilio SMS Notification, Perspective Correction, Twilio SMS/MMS Notification, EasyOCR, Detections List Roll-Up, Dimension Collapse, Grid Visualization, Google Gemini, Object Detection Model, Trace Visualization, QR Code Generator, Pixelate Visualization, OpenAI, Camera Calibration, Roboflow Dataset Upload, Buffer, Webhook Sink, Single-Label Classification Model, Object Detection Model, VLM as Detector, Background Subtraction, Bounding Box Visualization, Contrast Equalization, Halo Visualization, Model Comparison Visualization, Label Visualization, Slack Notification, Dynamic Zone, OpenAI, Circle Visualization, Image Contours, Background Color Visualization, Image Blur, Mask Visualization, VLM as Classifier, Size Measurement, Google Vision OCR, Llama 3.2 Vision, Color Visualization, Corner Visualization, Classification Label Visualization, Single-Label Classification Model, OpenAI, Clip Comparison, Line Counter Visualization, Ellipse Visualization, Icon Visualization, Model Monitoring Inference Aggregator, Image Slicer, Absolute Static Crop, Polygon Visualization, SIFT Comparison, Stability AI Inpainting, Keypoint Detection Model, Identify Changes, Relative Static Crop, SIFT, CSV Formatter, Text Display, Multi-Label Classification Model
• outputs: Florence-2 Model, Pixelate Visualization, Detections Consensus, Roboflow Dataset Upload, Detections Stitch, Roboflow Custom Metadata, Detections Merge, Detection Offset, Bounding Box Visualization, Byte Tracker, Model Comparison Visualization, Halo Visualization, Byte Tracker, Label Visualization, Dynamic Zone, Circle Visualization, Camera Focus, Overlap Filter, Background Color Visualization, Size Measurement, Mask Visualization, Blur Visualization, Time in Zone, Path Deviation, Bounding Rectangle, Detection Event Log, Roboflow Dataset Upload, Corner Visualization, Detections Transformation, Color Visualization, Detections Combine, Segment Anything 2 Model, Detections Classes Replacement, Florence-2 Model, Time in Zone, Ellipse Visualization, Icon Visualization, Byte Tracker, Dynamic Crop, Velocity, Line Counter, Model Monitoring Inference Aggregator, Time in Zone, Detections Stabilizer, Triangle Visualization, Dot Visualization, Polygon Visualization, Stability AI Inpainting, Crop Visualization, PTZ Tracking (ONVIF).md), Path Deviation, Perspective Correction, Distance Measurement, Detections List Roll-Up, Detections Filter, Line Counter, Trace Visualization

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds SAM 3 in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • model_id (roboflow_model_id): model version. You only need to change this for fine tuned sam3 models..
  • class_names (Union[string, list_of_values]): List of classes to recognise.
  • threshold (float): Threshold for predicted mask scores.

• output

  • predictions (instance_segmentation_prediction): Prediction with detected bounding boxes and segmentation masks in form of sv.Detections(...) object.

Example JSON definition of step SAM 3 in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/sam3@v1",
    "images": "$inputs.image",
    "model_id": "sam3/sam3_final",
    "class_names": [
        "car",
        "person"
    ],
    "threshold": 0.3
}