Anthropic Claude

v3

Class: AnthropicClaudeBlockV3 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.anthropic_claude.v3.AnthropicClaudeBlockV3

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Ask a question to Anthropic Claude model with vision capabilities.

You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:

• Open Prompt (unconstrained) - Use any prompt to generate a raw response

• Text Recognition (OCR) (ocr) - Model recognizes text in the image

• Visual Question Answering (visual-question-answering) - Model answers the question you submit in the prompt

• Captioning (short) (caption) - Model provides a short description of the image

• Captioning (detailed-caption) - Model provides a long description of the image

• Single-Label Classification (classification) - Model classifies the image content as one of the provided classes

• Multi-Label Classification (multi-label-classification) - Model classifies the image content as one or more of the provided classes

• Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image

• Structured Output Generation (structured-answering) - Model returns a JSON response with the specified fields

API Key Options

This block supports two API key modes:

1. Roboflow Managed API Key (Default) - Use rf_key:account to proxy requests through Roboflow's API:
2. Simplified setup - no Anthropic API key required
3. Secure - your workflow API key is used for authentication

4. Usage-based billing - charged per token based on the model used

5. Custom Anthropic API Key - Provide your own Anthropic API key:

6. Full control over API usage
7. You pay Anthropic directly

Type identifier

Use the following identifier in step "type" field: roboflow_core/anthropic_claude@v3to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
task_type	str	Task type to be performed by model. Value determines required parameters and output response..	❌
prompt	str	Text prompt to the Claude model.	✅
output_structure	Dict[str, str]	Dictionary with structure of expected JSON response.	❌
classes	List[str]	List of classes to be used.	✅
api_key	str	Your Anthropic API key or 'rf_key:account' to use Roboflow's managed API key.	✅
model_version	str	Model to be used.	✅
extended_thinking	bool	Enable extended thinking for deeper reasoning on complex tasks. Note: temperature cannot be used when extended thinking is enabled..	❌
thinking_budget_tokens	int	Maximum number of tokens for internal thinking when extended thinking is enabled. Higher values allow deeper reasoning but increase latency and cost. Must be less than max_tokens. Minimum: 1024..	❌
max_tokens	int	Maximum number of tokens the model can generate in its response..	❌
temperature	float	Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..	✅
max_image_size	int	Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.	✅
max_concurrent_requests	int	Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit Anthropic API limits..	❌

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 Anthropic Claude in version v3.

• inputs: Trace Visualization, Contrast Equalization, Circle Visualization, Background Color Visualization, Size Measurement, Slack Notification, VLM As Classifier, Color Visualization, Image Slicer, Florence-2 Model, Stability AI Inpainting, Reference Path Visualization, OpenAI, Corner Visualization, Clip Comparison, Pixel Color Count, Local File Sink, Relative Static Crop, Perspective Correction, Roboflow Dataset Upload, OpenAI, Model Monitoring Inference Aggregator, Instance Segmentation Model, Image Threshold, Pixelate Visualization, Object Detection Model, Dimension Collapse, Polygon Visualization, Ellipse Visualization, Email Notification, OCR Model, Cosine Similarity, CogVLM, Label Visualization, Image Slicer, Bounding Box Visualization, Google Vision OCR, Crop Visualization, Stitch OCR Detections, Twilio SMS/MMS Notification, Stitch OCR Detections, VLM As Detector, Image Blur, Halo Visualization, Clip Comparison, Anthropic Claude, Icon Visualization, SIFT, Triangle Visualization, Anthropic Claude, Image Contours, Morphological Transformation, Motion Detection, Line Counter, Detection Event Log, Gaze Detection, Stitch Images, SIFT Comparison, Heatmap Visualization, Blur Visualization, Detections List Roll-Up, OpenAI, Polygon Visualization, CSV Formatter, Mask Visualization, Email Notification, Stability AI Outpainting, Camera Calibration, LMM For Classification, Google Gemini, Anthropic Claude, Google Gemini, Single-Label Classification Model, Google Gemini, Dynamic Zone, Template Matching, Line Counter Visualization, Camera Focus, OpenAI, Webhook Sink, Image Convert Grayscale, Twilio SMS Notification, LMM, Multi-Label Classification Model, Camera Focus, Classification Label Visualization, Model Comparison Visualization, Roboflow Dataset Upload, Stability AI Image Generation, EasyOCR, SIFT Comparison, Polygon Zone Visualization, Distance Measurement, Grid Visualization, Background Subtraction, Halo Visualization, Florence-2 Model, Keypoint Visualization, QR Code Generator, Buffer, Line Counter, Depth Estimation, Text Display, Dot Visualization, Identify Changes, Llama 3.2 Vision, Roboflow Custom Metadata, Dynamic Crop, Image Preprocessing, Keypoint Detection Model, Absolute Static Crop
• outputs: Trace Visualization, Detections Consensus, Background Color Visualization, VLM As Classifier, Florence-2 Model, Reference Path Visualization, Corner Visualization, SAM 3, Pixel Color Count, Seg Preview, Perspective Correction, Roboflow Dataset Upload, OpenAI, Model Monitoring Inference Aggregator, Image Threshold, Object Detection Model, Email Notification, Label Visualization, Object Detection Model, Bounding Box Visualization, Google Vision OCR, Crop Visualization, VLM As Detector, Time in Zone, Image Blur, Path Deviation, Clip Comparison, Anthropic Claude, Triangle Visualization, Instance Segmentation Model, Heatmap Visualization, SAM 3, Time in Zone, Mask Visualization, Detections Stitch, Email Notification, Stability AI Outpainting, Time in Zone, Google Gemini, Segment Anything 2 Model, LMM For Classification, Anthropic Claude, Google Gemini, Google Gemini, Twilio SMS Notification, Keypoint Detection Model, Roboflow Dataset Upload, Stability AI Image Generation, SIFT Comparison, Polygon Zone Visualization, Distance Measurement, YOLO-World Model, Line Counter, Depth Estimation, Dot Visualization, Llama 3.2 Vision, PTZ Tracking (ONVIF).md), Dynamic Crop, Contrast Equalization, CLIP Embedding Model, Circle Visualization, Size Measurement, Slack Notification, Perception Encoder Embedding Model, Color Visualization, Stability AI Inpainting, OpenAI, Clip Comparison, Local File Sink, JSON Parser, Instance Segmentation Model, Polygon Visualization, Ellipse Visualization, CogVLM, VLM As Detector, SAM 3, Stitch OCR Detections, Twilio SMS/MMS Notification, Stitch OCR Detections, Moondream2, Halo Visualization, Icon Visualization, Anthropic Claude, Morphological Transformation, Line Counter, Motion Detection, Detections List Roll-Up, OpenAI, Polygon Visualization, Cache Get, Detections Classes Replacement, Line Counter Visualization, OpenAI, Webhook Sink, LMM, Model Comparison Visualization, Classification Label Visualization, VLM As Classifier, Grid Visualization, Halo Visualization, Florence-2 Model, Keypoint Visualization, QR Code Generator, Buffer, Text Display, Cache Set, Roboflow Custom Metadata, Image Preprocessing, Keypoint Detection Model, Path Deviation

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Anthropic Claude in version v3 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Claude model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[secret, ROBOFLOW_MANAGED_KEY, string]): Your Anthropic API key or 'rf_key:account' to use Roboflow's managed API key.
  • model_version (string): Model to be used.
  • temperature (float): Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..
  • max_image_size (integer): Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.

• output

  • output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
  • classes (list_of_values): List of values of any type.

Example JSON definition of step Anthropic Claude in version v3

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/anthropic_claude@v3",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "output_structure": {
        "my_key": "description"
    },
    "classes": [
        "class-a",
        "class-b"
    ],
    "api_key": "rf_key:account",
    "model_version": "claude-sonnet-4-5",
    "extended_thinking": "<block_does_not_provide_example>",
    "thinking_budget_tokens": "<block_does_not_provide_example>",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_image_size": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v2

Class: AnthropicClaudeBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.anthropic_claude.v2.AnthropicClaudeBlockV2

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Ask a question to Anthropic Claude model with vision capabilities.

You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:

• Open Prompt (unconstrained) - Use any prompt to generate a raw response

• Text Recognition (OCR) (ocr) - Model recognizes text in the image

• Visual Question Answering (visual-question-answering) - Model answers the question you submit in the prompt

• Captioning (short) (caption) - Model provides a short description of the image

• Captioning (detailed-caption) - Model provides a long description of the image

• Single-Label Classification (classification) - Model classifies the image content as one of the provided classes

• Multi-Label Classification (multi-label-classification) - Model classifies the image content as one or more of the provided classes

• Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image

• Structured Output Generation (structured-answering) - Model returns a JSON response with the specified fields

You need to provide your Anthropic API key to use the Claude model.

Type identifier

Use the following identifier in step "type" field: roboflow_core/anthropic_claude@v2to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
task_type	str	Task type to be performed by model. Value determines required parameters and output response..	❌
prompt	str	Text prompt to the Claude model.	✅
output_structure	Dict[str, str]	Dictionary with structure of expected JSON response.	❌
classes	List[str]	List of classes to be used.	✅
api_key	str	Your Anthropic API key.	✅
model_version	str	Model to be used.	✅
extended_thinking	bool	Enable extended thinking for deeper reasoning on complex tasks. Note: temperature cannot be used when extended thinking is enabled..	❌
thinking_budget_tokens	int	Maximum number of tokens for internal thinking when extended thinking is enabled. Higher values allow deeper reasoning but increase latency and cost. Must be less than max_tokens. Minimum: 1024..	❌
max_tokens	int	Maximum number of tokens the model can generate in its response..	❌
temperature	float	Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..	✅
max_image_size	int	Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.	✅
max_concurrent_requests	int	Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit Anthropic API limits..	❌

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 Anthropic Claude in version v2.

• inputs: Trace Visualization, Contrast Equalization, Circle Visualization, Background Color Visualization, Size Measurement, Slack Notification, VLM As Classifier, Color Visualization, Image Slicer, Florence-2 Model, Stability AI Inpainting, Reference Path Visualization, OpenAI, Corner Visualization, Clip Comparison, Pixel Color Count, Local File Sink, Relative Static Crop, Perspective Correction, Roboflow Dataset Upload, OpenAI, Model Monitoring Inference Aggregator, Instance Segmentation Model, Image Threshold, Pixelate Visualization, Object Detection Model, Dimension Collapse, Polygon Visualization, Ellipse Visualization, Email Notification, OCR Model, Cosine Similarity, CogVLM, Label Visualization, Image Slicer, Bounding Box Visualization, Google Vision OCR, Crop Visualization, Stitch OCR Detections, Twilio SMS/MMS Notification, Stitch OCR Detections, VLM As Detector, Image Blur, Halo Visualization, Clip Comparison, Anthropic Claude, Icon Visualization, SIFT, Triangle Visualization, Anthropic Claude, Image Contours, Morphological Transformation, Motion Detection, Line Counter, Detection Event Log, Gaze Detection, Stitch Images, SIFT Comparison, Heatmap Visualization, Blur Visualization, Detections List Roll-Up, OpenAI, Polygon Visualization, CSV Formatter, Mask Visualization, Email Notification, Stability AI Outpainting, Camera Calibration, LMM For Classification, Google Gemini, Anthropic Claude, Google Gemini, Single-Label Classification Model, Google Gemini, Dynamic Zone, Template Matching, Line Counter Visualization, Camera Focus, OpenAI, Webhook Sink, Image Convert Grayscale, Twilio SMS Notification, LMM, Multi-Label Classification Model, Camera Focus, Classification Label Visualization, Model Comparison Visualization, Roboflow Dataset Upload, Stability AI Image Generation, EasyOCR, SIFT Comparison, Polygon Zone Visualization, Distance Measurement, Grid Visualization, Background Subtraction, Halo Visualization, Florence-2 Model, Keypoint Visualization, QR Code Generator, Buffer, Line Counter, Depth Estimation, Text Display, Dot Visualization, Identify Changes, Llama 3.2 Vision, Roboflow Custom Metadata, Dynamic Crop, Image Preprocessing, Keypoint Detection Model, Absolute Static Crop
• outputs: Trace Visualization, Detections Consensus, Background Color Visualization, VLM As Classifier, Florence-2 Model, Reference Path Visualization, Corner Visualization, SAM 3, Pixel Color Count, Seg Preview, Perspective Correction, Roboflow Dataset Upload, OpenAI, Model Monitoring Inference Aggregator, Image Threshold, Object Detection Model, Email Notification, Label Visualization, Object Detection Model, Bounding Box Visualization, Google Vision OCR, Crop Visualization, VLM As Detector, Time in Zone, Image Blur, Path Deviation, Clip Comparison, Anthropic Claude, Triangle Visualization, Instance Segmentation Model, Heatmap Visualization, SAM 3, Time in Zone, Mask Visualization, Detections Stitch, Email Notification, Stability AI Outpainting, Time in Zone, Google Gemini, Segment Anything 2 Model, LMM For Classification, Anthropic Claude, Google Gemini, Google Gemini, Twilio SMS Notification, Keypoint Detection Model, Roboflow Dataset Upload, Stability AI Image Generation, SIFT Comparison, Polygon Zone Visualization, Distance Measurement, YOLO-World Model, Line Counter, Depth Estimation, Dot Visualization, Llama 3.2 Vision, PTZ Tracking (ONVIF).md), Dynamic Crop, Contrast Equalization, CLIP Embedding Model, Circle Visualization, Size Measurement, Slack Notification, Perception Encoder Embedding Model, Color Visualization, Stability AI Inpainting, OpenAI, Clip Comparison, Local File Sink, JSON Parser, Instance Segmentation Model, Polygon Visualization, Ellipse Visualization, CogVLM, VLM As Detector, SAM 3, Stitch OCR Detections, Twilio SMS/MMS Notification, Stitch OCR Detections, Moondream2, Halo Visualization, Icon Visualization, Anthropic Claude, Morphological Transformation, Line Counter, Motion Detection, Detections List Roll-Up, OpenAI, Polygon Visualization, Cache Get, Detections Classes Replacement, Line Counter Visualization, OpenAI, Webhook Sink, LMM, Model Comparison Visualization, Classification Label Visualization, VLM As Classifier, Grid Visualization, Halo Visualization, Florence-2 Model, Keypoint Visualization, QR Code Generator, Buffer, Text Display, Cache Set, Roboflow Custom Metadata, Image Preprocessing, Keypoint Detection Model, Path Deviation

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Anthropic Claude in version v2 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Claude model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[secret, string]): Your Anthropic API key.
  • model_version (string): Model to be used.
  • temperature (float): Temperature to sample from the model - value in range 0.0-1.0, the higher - the more random / "creative" the generations are. Cannot be used when extended_thinking is enabled..
  • max_image_size (integer): Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.

• output

  • output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
  • classes (list_of_values): List of values of any type.

Example JSON definition of step Anthropic Claude in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/anthropic_claude@v2",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "output_structure": {
        "my_key": "description"
    },
    "classes": [
        "class-a",
        "class-b"
    ],
    "api_key": "xxx-xxx",
    "model_version": "claude-sonnet-4-5",
    "extended_thinking": "<block_does_not_provide_example>",
    "thinking_budget_tokens": "<block_does_not_provide_example>",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_image_size": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v1

Class: AnthropicClaudeBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.anthropic_claude.v1.AnthropicClaudeBlockV1

Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning

Ask a question to Anthropic Claude model with vision capabilities.

You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:

• Open Prompt (unconstrained) - Use any prompt to generate a raw response

• Text Recognition (OCR) (ocr) - Model recognizes text in the image

• Visual Question Answering (visual-question-answering) - Model answers the question you submit in the prompt

• Captioning (short) (caption) - Model provides a short description of the image

• Captioning (detailed-caption) - Model provides a long description of the image

• Single-Label Classification (classification) - Model classifies the image content as one of the provided classes

• Multi-Label Classification (multi-label-classification) - Model classifies the image content as one or more of the provided classes

• Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image

• Structured Output Generation (structured-answering) - Model returns a JSON response with the specified fields

You need to provide your Anthropic API key to use the Claude model.

Type identifier

Use the following identifier in step "type" field: roboflow_core/anthropic_claude@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
task_type	str	Task type to be performed by model. Value determines required parameters and output response..	❌
prompt	str	Text prompt to the Claude model.	✅
output_structure	Dict[str, str]	Dictionary with structure of expected JSON response.	❌
classes	List[str]	List of classes to be used.	✅
api_key	str	Your Anthropic API key.	✅
model_version	str	Model to be used.	✅
max_tokens	int	Maximum number of tokens the model can generate in it's response..	❌
temperature	float	Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..	✅
max_image_size	int	Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.	✅
max_concurrent_requests	int	Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit Anthropic API limits..	❌

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 Anthropic Claude in version v1.

• inputs: Trace Visualization, Contrast Equalization, Circle Visualization, Background Color Visualization, Size Measurement, Slack Notification, VLM As Classifier, Color Visualization, Image Slicer, Florence-2 Model, Stability AI Inpainting, Reference Path Visualization, OpenAI, Corner Visualization, Clip Comparison, Pixel Color Count, Local File Sink, Relative Static Crop, Perspective Correction, Roboflow Dataset Upload, OpenAI, Model Monitoring Inference Aggregator, Instance Segmentation Model, Image Threshold, Pixelate Visualization, Object Detection Model, Dimension Collapse, Polygon Visualization, Ellipse Visualization, Email Notification, OCR Model, Cosine Similarity, CogVLM, Label Visualization, Image Slicer, Bounding Box Visualization, Google Vision OCR, Crop Visualization, Stitch OCR Detections, Twilio SMS/MMS Notification, Stitch OCR Detections, VLM As Detector, Image Blur, Halo Visualization, Clip Comparison, Anthropic Claude, Icon Visualization, SIFT, Triangle Visualization, Anthropic Claude, Image Contours, Morphological Transformation, Motion Detection, Line Counter, Detection Event Log, Gaze Detection, Stitch Images, SIFT Comparison, Heatmap Visualization, Blur Visualization, Detections List Roll-Up, OpenAI, Polygon Visualization, CSV Formatter, Mask Visualization, Email Notification, Stability AI Outpainting, Camera Calibration, LMM For Classification, Google Gemini, Anthropic Claude, Google Gemini, Single-Label Classification Model, Google Gemini, Dynamic Zone, Template Matching, Line Counter Visualization, Camera Focus, OpenAI, Webhook Sink, Image Convert Grayscale, Twilio SMS Notification, LMM, Multi-Label Classification Model, Camera Focus, Classification Label Visualization, Model Comparison Visualization, Roboflow Dataset Upload, Stability AI Image Generation, EasyOCR, SIFT Comparison, Polygon Zone Visualization, Distance Measurement, Grid Visualization, Background Subtraction, Halo Visualization, Florence-2 Model, Keypoint Visualization, QR Code Generator, Buffer, Line Counter, Depth Estimation, Text Display, Dot Visualization, Identify Changes, Llama 3.2 Vision, Roboflow Custom Metadata, Dynamic Crop, Image Preprocessing, Keypoint Detection Model, Absolute Static Crop
• outputs: Trace Visualization, Detections Consensus, Background Color Visualization, VLM As Classifier, Florence-2 Model, Reference Path Visualization, Corner Visualization, SAM 3, Pixel Color Count, Seg Preview, Perspective Correction, Roboflow Dataset Upload, OpenAI, Model Monitoring Inference Aggregator, Image Threshold, Object Detection Model, Email Notification, Label Visualization, Object Detection Model, Bounding Box Visualization, Google Vision OCR, Crop Visualization, VLM As Detector, Time in Zone, Image Blur, Path Deviation, Clip Comparison, Anthropic Claude, Triangle Visualization, Instance Segmentation Model, Heatmap Visualization, SAM 3, Time in Zone, Mask Visualization, Detections Stitch, Email Notification, Stability AI Outpainting, Time in Zone, Google Gemini, Segment Anything 2 Model, LMM For Classification, Anthropic Claude, Google Gemini, Google Gemini, Twilio SMS Notification, Keypoint Detection Model, Roboflow Dataset Upload, Stability AI Image Generation, SIFT Comparison, Polygon Zone Visualization, Distance Measurement, YOLO-World Model, Line Counter, Depth Estimation, Dot Visualization, Llama 3.2 Vision, PTZ Tracking (ONVIF).md), Dynamic Crop, Contrast Equalization, CLIP Embedding Model, Circle Visualization, Size Measurement, Slack Notification, Perception Encoder Embedding Model, Color Visualization, Stability AI Inpainting, OpenAI, Clip Comparison, Local File Sink, JSON Parser, Instance Segmentation Model, Polygon Visualization, Ellipse Visualization, CogVLM, VLM As Detector, SAM 3, Stitch OCR Detections, Twilio SMS/MMS Notification, Stitch OCR Detections, Moondream2, Halo Visualization, Icon Visualization, Anthropic Claude, Morphological Transformation, Line Counter, Motion Detection, Detections List Roll-Up, OpenAI, Polygon Visualization, Cache Get, Detections Classes Replacement, Line Counter Visualization, OpenAI, Webhook Sink, LMM, Model Comparison Visualization, Classification Label Visualization, VLM As Classifier, Grid Visualization, Halo Visualization, Florence-2 Model, Keypoint Visualization, QR Code Generator, Buffer, Text Display, Cache Set, Roboflow Custom Metadata, Image Preprocessing, Keypoint Detection Model, Path Deviation

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Anthropic Claude in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Claude model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[secret, string]): Your Anthropic API key.
  • model_version (string): Model to be used.
  • temperature (float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..
  • max_image_size (integer): Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.

• output

  • output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
  • classes (list_of_values): List of values of any type.

Example JSON definition of step Anthropic Claude in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/anthropic_claude@v1",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "output_structure": {
        "my_key": "description"
    },
    "classes": [
        "class-a",
        "class-b"
    ],
    "api_key": "xxx-xxx",
    "model_version": "claude-sonnet-4",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_image_size": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}