OpenAI

v4

Class: OpenAIBlockV4 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.openai.v4.OpenAIBlockV4

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 OpenAI's GPT models with vision capabilities (including GPT-5 and GPT-4o).

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

Provide your OpenAI API key or set the value to rf_key:account (or rf_key:user:<id>) to proxy requests through Roboflow's API.

Type identifier

Use the following identifier in step "type" field: roboflow_core/open_ai@v4to 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 OpenAI 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 OpenAI API key.	✅
model_version	str	Model to be used.	✅
reasoning_effort	str	Controls reasoning. Reducing can result in faster responses and fewer tokens. GPT-5.1 and higher models default to 'none' (no reasoning) and support 'none', 'low', 'medium', 'high'. GPT-5.2 also supports 'xhigh'. GPT-5 models default to 'medium' and support 'minimal', 'low', 'medium', 'high'..	✅
image_detail	str	Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..	✅
max_tokens	int	Maximum number of tokens the model can generate in its response. If not specified, the model will use its default limit. Minimum value is 16..	❌
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_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 OpenAI 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 OpenAI in version v4.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds OpenAI in version v4 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the OpenAI model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[string, ROBOFLOW_MANAGED_KEY, secret]): Your OpenAI API key.
  • model_version (string): Model to be used.
  • reasoning_effort (string): Controls reasoning. Reducing can result in faster responses and fewer tokens. GPT-5.1 and higher models default to 'none' (no reasoning) and support 'none', 'low', 'medium', 'high'. GPT-5.2 also supports 'xhigh'. GPT-5 models default to 'medium' and support 'minimal', 'low', 'medium', 'high'..
  • image_detail (string): Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..
  • temperature (float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..

• 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 OpenAI in version v4

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/open_ai@v4",
    "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": "gpt-5.1",
    "reasoning_effort": "<block_does_not_provide_example>",
    "image_detail": "auto",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v3

Class: OpenAIBlockV3 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.openai.v3.OpenAIBlockV3

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 OpenAI's GPT models with vision capabilities (including GPT-5 and GPT-4o).

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

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

Provide your OpenAI API key or set the value to rf_key:account (or rf_key:user:<id>) to proxy requests through Roboflow's API.

Type identifier

Use the following identifier in step "type" field: roboflow_core/open_ai@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 OpenAI 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 OpenAI API key.	✅
model_version	str	Model to be used.	✅
image_detail	str	Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..	✅
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_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 OpenAI 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 OpenAI in version v3.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the OpenAI model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[string, ROBOFLOW_MANAGED_KEY, secret]): Your OpenAI API key.
  • model_version (string): Model to be used.
  • image_detail (string): Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..
  • temperature (float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..

• 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 OpenAI in version v3

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/open_ai@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": "xxx-xxx",
    "model_version": "gpt-5",
    "image_detail": "auto",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v2

Class: OpenAIBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.openai.v2.OpenAIBlockV2

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 OpenAI's GPT models with vision capabilities (including GPT-4o and GPT-5).

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

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

You need to provide your OpenAI API key to use the GPT-4 with Vision model.

Type identifier

Use the following identifier in step "type" field: roboflow_core/open_ai@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 OpenAI 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 OpenAI API key.	✅
model_version	str	Model to be used.	✅
image_detail	str	Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..	✅
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_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 OpenAI 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 OpenAI in version v2.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the OpenAI model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[string, secret]): Your OpenAI API key.
  • model_version (string): Model to be used.
  • image_detail (string): Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..
  • temperature (float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..

• 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 OpenAI in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/open_ai@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": "gpt-4o",
    "image_detail": "auto",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v1

Class: OpenAIBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.openai.v1.OpenAIBlockV1

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 OpenAI's GPT-4 with Vision model.

You can specify arbitrary text prompts to the OpenAIBlock.

You need to provide your OpenAI API key to use the GPT-4 with Vision model.

This model was previously part of the LMM block.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
prompt	str	Text prompt to the OpenAI model.	✅
openai_api_key	str	Your OpenAI API key.	✅
openai_model	str	Model to be used.	✅
json_output_format	Dict[str, str]	Holds dictionary that maps name of requested output field into its description.	❌
image_detail	str	Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..	✅
max_tokens	int	Maximum number of tokens the model can generate in it's response..	❌

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 OpenAI in version v1.

• inputs: Contrast Equalization, Llama 3.2 Vision, Clip Comparison, Anthropic Claude, VLM as Detector, Local File Sink, Polygon Visualization, QR Code Generator, Image Blur, SIFT Comparison, Email Notification, Roboflow Dataset Upload, Text Display, Model Comparison Visualization, Camera Focus, SIFT, LMM, Google Vision OCR, Mask Visualization, Anthropic Claude, Relative Static Crop, Circle Visualization, EasyOCR, Pixelate Visualization, Stability AI Inpainting, Reference Path Visualization, Instance Segmentation Model, Perspective Correction, Ellipse Visualization, Crop Visualization, Halo Visualization, Image Threshold, Keypoint Detection Model, CSV Formatter, Florence-2 Model, Twilio SMS Notification, Image Convert Grayscale, Corner Visualization, Image Preprocessing, Icon Visualization, Background Subtraction, Image Contours, Image Slicer, Depth Estimation, Multi-Label Classification Model, Stitch Images, Dynamic Crop, Bounding Box Visualization, VLM as Classifier, Model Monitoring Inference Aggregator, Line Counter Visualization, Blur Visualization, Morphological Transformation, Camera Calibration, Polygon Zone Visualization, Single-Label Classification Model, Email Notification, Keypoint Visualization, OCR Model, Roboflow Custom Metadata, Google Gemini, OpenAI, Camera Focus, Trace Visualization, OpenAI, CogVLM, Color Visualization, Absolute Static Crop, Image Slicer, Dot Visualization, Label Visualization, Slack Notification, Florence-2 Model, Google Gemini, Google Gemini, Grid Visualization, Object Detection Model, LMM For Classification, OpenAI, Stitch OCR Detections, OpenAI, Classification Label Visualization, Background Color Visualization, Stability AI Outpainting, Stitch OCR Detections, Roboflow Dataset Upload, Twilio SMS/MMS Notification, Anthropic Claude, Triangle Visualization, Stability AI Image Generation, Webhook Sink
• outputs: Contrast Equalization, Clip Comparison, VLM as Detector, Detections Transformation, Polygon Visualization, Image Blur, SIFT Comparison, First Non Empty Or Default, Text Display, SIFT, Moondream2, Qwen3-VL, Google Vision OCR, Pixelate Visualization, Time in Zone, VLM as Classifier, Detection Offset, Detections Filter, Instance Segmentation Model, Perspective Correction, Halo Visualization, Image Threshold, Path Deviation, Keypoint Detection Model, CSV Formatter, Florence-2 Model, Twilio SMS Notification, Detections Stabilizer, Image Convert Grayscale, Perception Encoder Embedding Model, Corner Visualization, Dynamic Zone, Identify Changes, Icon Visualization, Expression, SAM 3, Qwen2.5-VL, Detections Consensus, Multi-Label Classification Model, Detections Stitch, Dynamic Crop, QR Code Detection, Continue If, Bounding Box Visualization, YOLO-World Model, Detection Event Log, Detections Classes Replacement, Blur Visualization, Camera Calibration, Line Counter, Dominant Color, Path Deviation, OpenAI, Camera Focus, Trace Visualization, CogVLM, Image Slicer, Absolute Static Crop, Dot Visualization, Label Visualization, Slack Notification, Google Gemini, Object Detection Model, LMM For Classification, Stitch OCR Detections, OpenAI, Classification Label Visualization, Stitch OCR Detections, Byte Tracker, Twilio SMS/MMS Notification, Velocity, Anthropic Claude, Gaze Detection, Clip Comparison, VLM as Detector, Webhook Sink, Llama 3.2 Vision, SIFT Comparison, Anthropic Claude, Delta Filter, Local File Sink, QR Code Generator, Time in Zone, SmolVLM2, Email Notification, CLIP Embedding Model, Roboflow Dataset Upload, Motion Detection, Model Comparison Visualization, Camera Focus, PTZ Tracking (ONVIF).md), LMM, Byte Tracker, Single-Label Classification Model, SAM 3, Mask Visualization, Anthropic Claude, Relative Static Crop, Cosine Similarity, Object Detection Model, Detections Merge, Keypoint Detection Model, Circle Visualization, Seg Preview, Property Definition, EasyOCR, Stability AI Inpainting, Multi-Label Classification Model, Reference Path Visualization, Time in Zone, Detections Combine, Crop Visualization, Ellipse Visualization, Overlap Filter, Line Counter, Image Preprocessing, Barcode Detection, Detections List Roll-Up, Segment Anything 2 Model, Background Subtraction, Image Slicer, Image Contours, Cache Set, Depth Estimation, Pixel Color Count, Stitch Images, VLM as Classifier, Cache Get, Model Monitoring Inference Aggregator, Instance Segmentation Model, Line Counter Visualization, Morphological Transformation, Polygon Zone Visualization, Single-Label Classification Model, Email Notification, Keypoint Visualization, Distance Measurement, Roboflow Custom Metadata, Google Gemini, OCR Model, OpenAI, Size Measurement, Color Visualization, Data Aggregator, Byte Tracker, Identify Outliers, Buffer, Florence-2 Model, Google Gemini, JSON Parser, Grid Visualization, Rate Limiter, OpenAI, Template Matching, Dimension Collapse, Bounding Rectangle, Background Color Visualization, Roboflow Dataset Upload, Stability AI Outpainting, SAM 3, Triangle Visualization, Stability AI Image Generation

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the OpenAI model.
  • openai_api_key (Union[string, secret]): Your OpenAI API key.
  • openai_model (string): Model to be used.
  • image_detail (string): Indicates the image's quality, with 'high' suggesting it is of high resolution and should be processed or displayed with high fidelity..

• output

  • parent_id (parent_id): Identifier of parent for step output.
  • root_parent_id (parent_id): Identifier of parent for step output.
  • image (image_metadata): Dictionary with image metadata required by supervision.
  • structured_output (dictionary): Dictionary.
  • raw_output (string): String value.
  • * (*): Equivalent of any element.

Example JSON definition of step OpenAI in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/open_ai@v1",
    "images": "$inputs.image",
    "prompt": "my prompt",
    "openai_api_key": "xxx-xxx",
    "openai_model": "gpt-4o",
    "json_output_format": {
        "count": "number of cats in the picture"
    },
    "image_detail": "auto",
    "max_tokens": 450
}