MoonshotAI Kimi¶
v2¶
Class: KimiOpenrouterBlockV2 (there are multiple versions of this block)
Source: inference.core.workflows.core_steps.models.foundation.kimi_openrouter.v2.KimiOpenrouterBlockV2
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 Moonshot AI Kimi vision-language models served via OpenRouter.
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 providers and model variants¶
Kimi is exposed via OpenRouter. By default this block uses
the Roboflow-managed OpenRouter key and bills your Roboflow credits — no extra
setup needed. To bypass Roboflow billing, paste your own sk-or-... key into the
api_key field.
The privacy_level field controls which OpenRouter providers may serve the request:
- No data collection (default) – providers may not train on your inputs.
- Allow data collection – broader provider pool.
- Zero data retention – strictest, restricts to providers that retain nothing.
💡 Further reading and Acceptable Use Policy¶
Model license
Check the Moonshot AI Kimi license terms before use.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/kimi_openrouter@v2to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
api_key |
str |
OpenRouter API key. Defaults to Roboflow's managed key, billed in credits via Roboflow. Provide your own sk-or-... key to call OpenRouter directly without Roboflow billing.. |
✅ |
privacy_level |
str |
Provider privacy filter. Stricter levels reduce the pool of providers and may increase per-call cost on the managed key.. | ❌ |
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 0.0-2.0, the higher - the more random / "creative" the generations are.. | ✅ |
max_concurrent_requests |
int |
Number of concurrent requests for batches of images. If not given - block defaults to value configured globally in Workflows Execution Engine. Restrict if you hit rate limits.. | ❌ |
task_type |
str |
Task type to be performed by model. Value determines required parameters and output response.. | ❌ |
prompt |
str |
Text prompt to the Kimi model. | ✅ |
output_structure |
Dict[str, str] |
Dictionary with structure of expected JSON response. | ❌ |
classes |
List[str] |
List of classes to be used. | ✅ |
model_version |
str |
Model to be used. | ✅ |
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 MoonshotAI Kimi in version v2.
- inputs:
Stability AI Outpainting,Motion Detection,Contrast Enhancement,Camera Focus,Cosine Similarity,Image Preprocessing,Object Detection Model,Corner Visualization,Roboflow Vision Events,Ellipse Visualization,Heatmap Visualization,Trace Visualization,OpenAI,Email Notification,Keypoint Visualization,Model Comparison Visualization,Polygon Zone Visualization,Dynamic Crop,Polygon Visualization,GLM-OCR,QR Code Generator,Stitch Images,OpenRouter,Model Monitoring Inference Aggregator,Clip Comparison,Image Blur,Dynamic Zone,Detections List Roll-Up,Buffer,Google Gemini,Pixelate Visualization,EasyOCR,SIFT,Contrast Equalization,Image Threshold,Instance Segmentation Model,Polygon Visualization,Anthropic Claude,Halo Visualization,Roboflow Custom Metadata,Florence-2 Model,Local File Sink,Icon Visualization,Single-Label Classification Model,Image Contours,OpenAI,Grid Visualization,Size Measurement,LMM,Image Convert Grayscale,Reference Path Visualization,Stitch OCR Detections,Keypoint Detection Model,SIFT Comparison,Identify Changes,Roboflow Dataset Upload,CSV Formatter,S3 Sink,OpenAI-Compatible LLM,Morphological Transformation,Crop Visualization,Blur Visualization,Qwen-VL,Mask Visualization,Stability AI Image Generation,Stitch OCR Detections,Google Gemma API,Image Slicer,Qwen 3.5 API,Background Color Visualization,Slack Notification,Anthropic Claude,Dimension Collapse,Qwen 3.6 API,Webhook Sink,Color Visualization,Bounding Box Visualization,Google Gemma,Relative Static Crop,CogVLM,Llama 3.2 Vision,Qwen3.5-VL,Camera Focus,Google Vision OCR,Google Gemini,Llama 3.2 Vision,Twilio SMS Notification,Anthropic Claude,OpenAI,Image Slicer,Depth Estimation,Multi-Label Classification Model,Gaze Detection,Classification Label Visualization,Florence-2 Model,MoonshotAI Kimi,MoonshotAI Kimi,Dot Visualization,Background Subtraction,Roboflow Dataset Upload,Stability AI Inpainting,Label Visualization,Absolute Static Crop,Google Gemini,VLM As Classifier,Email Notification,Camera Calibration,Halo Visualization,OpenAI,Clip Comparison,LMM For Classification,Text Display,Circle Visualization,Line Counter Visualization,OCR Model,VLM As Detector,Image Stack,Twilio SMS/MMS Notification,Morphological Transformation,Triangle Visualization,Perspective Correction - outputs:
Stability AI Outpainting,CLIP Embedding Model,SAM 3,Motion Detection,Seg Preview,Corner Visualization,Ellipse Visualization,Image Preprocessing,Roboflow Vision Events,Object Detection Model,Heatmap Visualization,Trace Visualization,VLM As Classifier,Time in Zone,OpenAI,Email Notification,Keypoint Visualization,Detections Consensus,Model Comparison Visualization,YOLO-World Model,JSON Parser,Polygon Zone Visualization,Dynamic Crop,Polygon Visualization,QR Code Generator,GLM-OCR,OpenRouter,Model Monitoring Inference Aggregator,Clip Comparison,Image Blur,Cache Get,Detections Stitch,Time in Zone,Detections List Roll-Up,Segment Anything 2 Model,Instance Segmentation Model,Google Gemini,Buffer,Contrast Equalization,Image Threshold,Instance Segmentation Model,Polygon Visualization,Anthropic Claude,Halo Visualization,Roboflow Custom Metadata,Keypoint Detection Model,Florence-2 Model,Local File Sink,Icon Visualization,OpenAI,SAM 3,Grid Visualization,VLM As Detector,Size Measurement,Multi-Label Classification Model,Object Detection Model,LMM,Reference Path Visualization,Stitch OCR Detections,Keypoint Detection Model,SIFT Comparison,Roboflow Dataset Upload,S3 Sink,Cache Set,OpenAI-Compatible LLM,Morphological Transformation,Object Detection Model,Mask Visualization,Stability AI Image Generation,Qwen-VL,Crop Visualization,Stitch OCR Detections,Google Gemma API,Qwen 3.5 API,Path Deviation,Perception Encoder Embedding Model,Background Color Visualization,Slack Notification,Anthropic Claude,Qwen 3.6 API,Webhook Sink,Color Visualization,Bounding Box Visualization,Google Gemma,CogVLM,Path Deviation,Llama 3.2 Vision,Instance Segmentation Model,Instance Segmentation Model,Google Vision OCR,Google Gemini,SAM 3,Distance Measurement,Single-Label Classification Model,Llama 3.2 Vision,Twilio SMS Notification,Moondream2,Anthropic Claude,OpenAI,Depth Estimation,Classification Label Visualization,PTZ Tracking (ONVIF),MoonshotAI Kimi,Florence-2 Model,Time in Zone,MoonshotAI Kimi,Line Counter,Dot Visualization,Keypoint Detection Model,Roboflow Dataset Upload,Stability AI Inpainting,Semantic Segmentation Model,Line Counter,Detections Classes Replacement,Label Visualization,Google Gemini,VLM As Classifier,Email Notification,Halo Visualization,OpenAI,Pixel Color Count,Clip Comparison,LMM For Classification,Text Display,Circle Visualization,Line Counter Visualization,VLM As Detector,Twilio SMS/MMS Notification,Morphological Transformation,Triangle Visualization,Perspective Correction
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
MoonshotAI Kimi in version v2 has.
Bindings
-
input
api_key(Union[ROBOFLOW_MANAGED_KEY,secret,string]): OpenRouter API key. Defaults to Roboflow's managed key, billed in credits via Roboflow. Provide your ownsk-or-...key to call OpenRouter directly without Roboflow billing..temperature(float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..images(image): The image to infer on..prompt(string): Text prompt to the Kimi model.classes(list_of_values): List of classes to be used.model_version(string): Model to be used.
-
output
output(Union[string,language_model_output]): String value ifstringor LLM / VLM output iflanguage_model_output.classes(list_of_values): List of values of any type.
Example JSON definition of step MoonshotAI Kimi in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/kimi_openrouter@v2",
"api_key": "rf_key:account",
"privacy_level": "<block_does_not_provide_example>",
"max_tokens": "<block_does_not_provide_example>",
"temperature": "<block_does_not_provide_example>",
"max_concurrent_requests": "<block_does_not_provide_example>",
"images": "$inputs.image",
"task_type": "<block_does_not_provide_example>",
"prompt": "my prompt",
"output_structure": {
"my_key": "description"
},
"classes": [
"class-a",
"class-b"
],
"model_version": "Kimi K2.6 - OpenRouter"
}
v1¶
Class: KimiOpenRouterBlockV1 (there are multiple versions of this block)
Source: inference.core.workflows.core_steps.models.foundation.kimi_openrouter.v1.KimiOpenRouterBlockV1
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 Moonshot AI Kimi vision-language models served via OpenRouter.
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 providers and model variants¶
Kimi is exposed via OpenRouter API and we require passing an OpenRouter API Key to run.
Pick a specific model version from the model_version dropdown - new Kimi releases
will be added to this list as they become available on OpenRouter.
API Usage Charges
OpenRouter is an external third party providing access to the model and incurring charges on the usage. Please check pricing on openrouter.ai before use.
💡 Further reading and Acceptable Use Policy¶
Model license
Check the Moonshot AI Kimi license terms before use.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/kimi_openrouter@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 Kimi 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 OpenRouter 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 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 MoonshotAI Kimi in version v1.
- inputs:
Stability AI Outpainting,Motion Detection,Contrast Enhancement,Camera Focus,Image Preprocessing,Corner Visualization,Ellipse Visualization,Object Detection Model,Roboflow Vision Events,Cosine Similarity,Heatmap Visualization,Trace Visualization,OpenAI,Email Notification,Keypoint Visualization,Model Comparison Visualization,Polygon Zone Visualization,Dynamic Crop,Polygon Visualization,QR Code Generator,GLM-OCR,Stitch Images,OpenRouter,Image Blur,Model Monitoring Inference Aggregator,Clip Comparison,Dynamic Zone,Detections List Roll-Up,Buffer,Google Gemini,Pixelate Visualization,EasyOCR,SIFT,Contrast Equalization,Image Threshold,Instance Segmentation Model,Polygon Visualization,Anthropic Claude,Halo Visualization,Roboflow Custom Metadata,Florence-2 Model,Local File Sink,Icon Visualization,Single-Label Classification Model,Image Contours,OpenAI,Grid Visualization,Size Measurement,LMM,Image Convert Grayscale,Reference Path Visualization,Stitch OCR Detections,Keypoint Detection Model,SIFT Comparison,Identify Changes,Roboflow Dataset Upload,CSV Formatter,S3 Sink,OpenAI-Compatible LLM,Morphological Transformation,Crop Visualization,Blur Visualization,Mask Visualization,Stability AI Image Generation,Qwen-VL,Stitch OCR Detections,Google Gemma API,Image Slicer,Qwen 3.5 API,Background Color Visualization,Slack Notification,Anthropic Claude,Dimension Collapse,Qwen 3.6 API,Webhook Sink,Color Visualization,Bounding Box Visualization,Google Gemma,Relative Static Crop,CogVLM,Llama 3.2 Vision,Qwen3.5-VL,Camera Focus,Google Vision OCR,Google Gemini,Llama 3.2 Vision,Twilio SMS Notification,Anthropic Claude,Image Slicer,Depth Estimation,OpenAI,Multi-Label Classification Model,Gaze Detection,Classification Label Visualization,Florence-2 Model,MoonshotAI Kimi,MoonshotAI Kimi,Dot Visualization,Background Subtraction,Roboflow Dataset Upload,Stability AI Inpainting,Label Visualization,Absolute Static Crop,Google Gemini,VLM As Classifier,Camera Calibration,Halo Visualization,Email Notification,OpenAI,Clip Comparison,LMM For Classification,Text Display,Circle Visualization,Line Counter Visualization,OCR Model,VLM As Detector,Image Stack,Morphological Transformation,Twilio SMS/MMS Notification,Triangle Visualization,Perspective Correction - outputs:
Stability AI Outpainting,CLIP Embedding Model,SAM 3,Motion Detection,Seg Preview,Corner Visualization,Ellipse Visualization,Image Preprocessing,Roboflow Vision Events,Object Detection Model,Heatmap Visualization,Trace Visualization,VLM As Classifier,Time in Zone,OpenAI,Email Notification,Keypoint Visualization,Detections Consensus,Model Comparison Visualization,YOLO-World Model,JSON Parser,Polygon Zone Visualization,Dynamic Crop,Polygon Visualization,QR Code Generator,GLM-OCR,OpenRouter,Model Monitoring Inference Aggregator,Clip Comparison,Image Blur,Cache Get,Detections Stitch,Time in Zone,Detections List Roll-Up,Segment Anything 2 Model,Instance Segmentation Model,Google Gemini,Buffer,Contrast Equalization,Image Threshold,Instance Segmentation Model,Polygon Visualization,Anthropic Claude,Halo Visualization,Roboflow Custom Metadata,Keypoint Detection Model,Florence-2 Model,Local File Sink,Icon Visualization,OpenAI,SAM 3,Grid Visualization,VLM As Detector,Size Measurement,Multi-Label Classification Model,Object Detection Model,LMM,Reference Path Visualization,Stitch OCR Detections,Keypoint Detection Model,SIFT Comparison,Roboflow Dataset Upload,S3 Sink,Cache Set,OpenAI-Compatible LLM,Morphological Transformation,Object Detection Model,Mask Visualization,Stability AI Image Generation,Qwen-VL,Crop Visualization,Stitch OCR Detections,Google Gemma API,Qwen 3.5 API,Path Deviation,Perception Encoder Embedding Model,Background Color Visualization,Slack Notification,Anthropic Claude,Qwen 3.6 API,Webhook Sink,Color Visualization,Bounding Box Visualization,Google Gemma,CogVLM,Path Deviation,Llama 3.2 Vision,Instance Segmentation Model,Instance Segmentation Model,Google Vision OCR,Google Gemini,SAM 3,Distance Measurement,Single-Label Classification Model,Llama 3.2 Vision,Twilio SMS Notification,Moondream2,Anthropic Claude,OpenAI,Depth Estimation,Classification Label Visualization,PTZ Tracking (ONVIF),MoonshotAI Kimi,Florence-2 Model,Time in Zone,MoonshotAI Kimi,Line Counter,Dot Visualization,Keypoint Detection Model,Roboflow Dataset Upload,Stability AI Inpainting,Semantic Segmentation Model,Line Counter,Detections Classes Replacement,Label Visualization,Google Gemini,VLM As Classifier,Email Notification,Halo Visualization,OpenAI,Pixel Color Count,Clip Comparison,LMM For Classification,Text Display,Circle Visualization,Line Counter Visualization,VLM As Detector,Twilio SMS/MMS Notification,Morphological Transformation,Triangle Visualization,Perspective Correction
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
MoonshotAI Kimi in version v1 has.
Bindings
-
input
images(image): The image to infer on..prompt(string): Text prompt to the Kimi model.classes(list_of_values): List of classes to be used.api_key(Union[secret,string]): Your OpenRouter 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 ifstringor LLM / VLM output iflanguage_model_output.classes(list_of_values): List of values of any type.
Example JSON definition of step MoonshotAI Kimi in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/kimi_openrouter@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": "Kimi K2.6 - OpenRouter",
"max_tokens": "<block_does_not_provide_example>",
"temperature": "<block_does_not_provide_example>",
"max_concurrent_requests": "<block_does_not_provide_example>"
}