Qwen 3.5 API¶
Class: Qwen35OpenRouterBlockV1
Source: inference.core.workflows.core_steps.models.foundation.qwen3_5_openrouter.v1.Qwen35OpenRouterBlockV1
Ask a question to Qwen 3.5 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¶
Qwen 3.5 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 Qwen 3.5 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 Qwen license terms before use.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/qwen3_5_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 Qwen 3.5 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 Qwen 3.5 API in version v1.
- inputs:
Roboflow Dataset Upload,Line Counter Visualization,OCR Model,Image Slicer,Gaze Detection,Instance Segmentation Model,Color Visualization,Ellipse Visualization,Polygon Visualization,Relative Static Crop,Webhook Sink,Trace Visualization,Stitch OCR Detections,Camera Focus,Qwen 3.5 API,OpenAI,Buffer,Size Measurement,Image Threshold,Heatmap Visualization,Florence-2 Model,Halo Visualization,GLM-OCR,Dot Visualization,S3 Sink,Twilio SMS Notification,Model Monitoring Inference Aggregator,Google Gemini,Roboflow Dataset Upload,Dynamic Zone,Clip Comparison,Pixelate Visualization,Twilio SMS/MMS Notification,Polygon Zone Visualization,Motion Detection,Blur Visualization,Background Subtraction,Text Display,CSV Formatter,Stability AI Image Generation,Perspective Correction,Anthropic Claude,Bounding Box Visualization,Depth Estimation,Stability AI Inpainting,Polygon Visualization,SIFT,Roboflow Vision Events,Google Gemini,Label Visualization,Grid Visualization,Qwen3.5-VL,Contrast Equalization,Triangle Visualization,Halo Visualization,Circle Visualization,Mask Visualization,OpenAI,MoonshotAI Kimi,Llama 3.2 Vision,Email Notification,Slack Notification,Object Detection Model,Stability AI Outpainting,Email Notification,Google Gemma API,Google Vision OCR,Image Preprocessing,Google Gemini,EasyOCR,Cosine Similarity,OpenAI,Anthropic Claude,Model Comparison Visualization,Roboflow Custom Metadata,Single-Label Classification Model,VLM As Classifier,Detections List Roll-Up,Stitch Images,Qwen 3.6 API,SIFT Comparison,Morphological Transformation,CogVLM,Crop Visualization,Camera Calibration,Florence-2 Model,Icon Visualization,Local File Sink,Image Contours,Reference Path Visualization,Dimension Collapse,Anthropic Claude,Clip Comparison,VLM As Detector,LMM,Identify Changes,Classification Label Visualization,Image Slicer,Absolute Static Crop,Image Blur,Multi-Label Classification Model,Image Convert Grayscale,OpenAI,Corner Visualization,Dynamic Crop,Keypoint Visualization,QR Code Generator,Camera Focus,LMM For Classification,Morphological Transformation,Keypoint Detection Model,Contrast Enhancement,Background Color Visualization,Stitch OCR Detections - outputs:
Roboflow Dataset Upload,Line Counter Visualization,Distance Measurement,Instance Segmentation Model,Color Visualization,Multi-Label Classification Model,Ellipse Visualization,Polygon Visualization,Single-Label Classification Model,Detections Consensus,Detections Classes Replacement,Cache Set,Webhook Sink,Trace Visualization,Stitch OCR Detections,Qwen 3.5 API,Object Detection Model,OpenAI,Buffer,SAM 3,Size Measurement,Image Threshold,Heatmap Visualization,Florence-2 Model,Halo Visualization,Path Deviation,GLM-OCR,Dot Visualization,S3 Sink,Path Deviation,Semantic Segmentation Model,Twilio SMS Notification,Seg Preview,Model Monitoring Inference Aggregator,Google Gemini,Roboflow Dataset Upload,Clip Comparison,VLM As Classifier,Line Counter,Twilio SMS/MMS Notification,Polygon Zone Visualization,Motion Detection,Text Display,Stability AI Image Generation,Perspective Correction,Anthropic Claude,Line Counter,Bounding Box Visualization,Depth Estimation,Stability AI Inpainting,Polygon Visualization,Roboflow Vision Events,VLM As Detector,Google Gemini,Label Visualization,Grid Visualization,Contrast Equalization,Triangle Visualization,Halo Visualization,Circle Visualization,Segment Anything 2 Model,Mask Visualization,OpenAI,MoonshotAI Kimi,Llama 3.2 Vision,Email Notification,Slack Notification,CLIP Embedding Model,Detections Stitch,Object Detection Model,Email Notification,Google Gemma API,Stability AI Outpainting,Google Vision OCR,Google Gemini,Image Preprocessing,Object Detection Model,OpenAI,Anthropic Claude,Time in Zone,Model Comparison Visualization,Roboflow Custom Metadata,YOLO-World Model,Perception Encoder Embedding Model,Instance Segmentation Model,VLM As Classifier,Detections List Roll-Up,Qwen 3.6 API,SIFT Comparison,Morphological Transformation,Instance Segmentation Model,CogVLM,Crop Visualization,Florence-2 Model,Time in Zone,SAM 3,Local File Sink,Icon Visualization,JSON Parser,Keypoint Detection Model,Time in Zone,Reference Path Visualization,Anthropic Claude,Clip Comparison,VLM As Detector,LMM,Pixel Color Count,Classification Label Visualization,Image Blur,SAM 3,OpenAI,Corner Visualization,Keypoint Detection Model,Dynamic Crop,Keypoint Visualization,Moondream2,QR Code Generator,LMM For Classification,Morphological Transformation,Keypoint Detection Model,Background Color Visualization,PTZ Tracking (ONVIF),Stitch OCR Detections,Cache Get
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Qwen 3.5 API in version v1 has.
Bindings
-
input
images(image): The image to infer on..prompt(string): Text prompt to the Qwen 3.5 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 Qwen 3.5 API in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/qwen3_5_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": "Qwen 3.5 27B - OpenRouter",
"max_tokens": "<block_does_not_provide_example>",
"temperature": "<block_does_not_provide_example>",
"max_concurrent_requests": "<block_does_not_provide_example>"
}