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

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, secret, ROBOFLOW_MANAGED_KEY]): 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..

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

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

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>"
}