Google Gemini

v3

Class: GoogleGeminiBlockV3 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.google_gemini.v3.GoogleGeminiBlockV3

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 Google's Gemini 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 Google AI 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 Google AI API Key - Provide your own Google AI API key:

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

WARNING!

This block makes use of /v1beta API of Google Gemini model - the implementation may change in the future, without guarantee of backward compatibility.

Type identifier

Use the following identifier in step "type" field: roboflow_core/google_gemini@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 Gemini 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 Google AI API key or 'rf_key:account' to use Roboflow's managed API key.	✅
model_version	str	Model to be used.	✅
thinking_level	str	Controls the depth of internal reasoning for Gemini 3+ models. 'low' minimizes latency and cost (best for simple tasks), 'high' maximizes reasoning depth (default). Only supported by Gemini 3 and newer models..	✅
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_tokens	int	Maximum number of tokens the model can generate in it's response. If not specified, the model will use its default limit..	❌
google_code_execution	bool	Enable native code execution for the Gemini model..	✅
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 Google Gemini 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 Google Gemini in version v3.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Gemini model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[string, ROBOFLOW_MANAGED_KEY, secret]): Your Google AI API key or 'rf_key:account' to use Roboflow's managed API key.
  • model_version (string): Model to be used.
  • thinking_level (string): Controls the depth of internal reasoning for Gemini 3+ models. 'low' minimizes latency and cost (best for simple tasks), 'high' maximizes reasoning depth (default). Only supported by Gemini 3 and newer models..
  • temperature (float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..
  • google_code_execution (boolean): Enable native code execution for the Gemini model..

• 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 Google Gemini in version v3

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/google_gemini@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": "gemini-3-pro-preview",
    "thinking_level": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_tokens": "<block_does_not_provide_example>",
    "google_code_execution": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v2

Class: GoogleGeminiBlockV2 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.google_gemini.v2.GoogleGeminiBlockV2

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 Google's Gemini 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 Google AI API key to use the Gemini model.

WARNING!

This block makes use of /v1beta API of Google Gemini model - the implementation may change in the future, without guarantee of backward compatibility.

Type identifier

Use the following identifier in step "type" field: roboflow_core/google_gemini@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 Gemini 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 Google AI API key.	✅
model_version	str	Model to be used.	✅
thinking_level	str	Controls the depth of internal reasoning for Gemini 3+ models. 'low' minimizes latency and cost (best for simple tasks), 'high' maximizes reasoning depth (default). Only supported by Gemini 3 and newer models..	✅
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_tokens	int	Maximum number of tokens the model can generate in it's response. If not specified, the model will use its default limit..	❌
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 Google Gemini 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 Google Gemini in version v2.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Gemini model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[string, secret]): Your Google AI API key.
  • model_version (string): Model to be used.
  • thinking_level (string): Controls the depth of internal reasoning for Gemini 3+ models. 'low' minimizes latency and cost (best for simple tasks), 'high' maximizes reasoning depth (default). Only supported by Gemini 3 and newer models..
  • 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 Google Gemini in version v2

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/google_gemini@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": "gemini-3-pro-preview",
    "thinking_level": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_tokens": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}

v1

Class: GoogleGeminiBlockV1 (there are multiple versions of this block)

Source: inference.core.workflows.core_steps.models.foundation.google_gemini.v1.GoogleGeminiBlockV1

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 Google's Gemini 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 Google AI API key to use the Gemini model.

WARNING!

This block makes use of /v1beta API of Google Gemini model - the implementation may change in the future, without guarantee of backward compatibility.

Type identifier

Use the following identifier in step "type" field: roboflow_core/google_gemini@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 Gemini 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 Google AI 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_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 Google Gemini 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 Google Gemini in version v1.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Gemini model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[string, secret]): Your Google AI 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..

• 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 Google Gemini in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/google_gemini@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": "gemini-2.5-pro",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}