Qwen3.5-VL¶
Deprecated
Use the unified Qwen-VL block (roboflow_core/qwen_vlm@v1), which exposes Qwen 3.5 VL alongside other Qwen variants and the OpenRouter passthrough.
Class: Qwen35VLBlockV1
Source: inference.core.workflows.core_steps.models.foundation.qwen3_5vl.v1.Qwen35VLBlockV1
This workflow block runs Qwen3.5-VL—a vision language model that accepts an image and an optional text prompt—and returns a text answer based on a conversation template.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/qwen3_5vl@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 |
Optional text prompt to provide additional context to Qwen3.5-VL. Otherwise it will just be a default one, which may affect the desired model behavior.. | ❌ |
model_version |
str |
The Qwen3.5-VL model to be used for inference.. | ✅ |
system_prompt |
str |
Optional system prompt to provide additional context to Qwen3.5-VL.. | ❌ |
enable_thinking |
bool |
If true, enables Qwen3.5-VL's thinking mode, which allows the model to generate reasoning tokens before answering. The thinking output will be returned in the 'thinking' field.. | ❌ |
max_new_tokens |
int |
Maximum number of tokens to generate. If not set, the model's default will be used. Consider increasing for thinking mode.. | ❌ |
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 Qwen3.5-VL in version v1.
- inputs:
Single-Label Classification Model,Perspective Correction,Object Detection Model,Stability AI Inpainting,Image Convert Grayscale,Keypoint Detection Model,Morphological Transformation,Object Detection Model,Pixelate Visualization,Stitch Images,QR Code Generator,Instance Segmentation Model,Image Slicer,Image Preprocessing,SIFT,Line Counter Visualization,Polygon Zone Visualization,Image Threshold,Image Slicer,Semantic Segmentation Model,Corner Visualization,Dynamic Crop,Stability AI Outpainting,Halo Visualization,Heatmap Visualization,Keypoint Visualization,Color Visualization,Semantic Segmentation Model,Blur Visualization,Stability AI Image Generation,Camera Focus,Label Visualization,Classification Label Visualization,Camera Focus,Camera Calibration,Morphological Transformation,Trace Visualization,Contrast Enhancement,Bounding Box Visualization,Reference Path Visualization,Depth Estimation,Halo Visualization,Multi-Label Classification Model,Ellipse Visualization,Model Comparison Visualization,Dot Visualization,SIFT Comparison,Image Contours,Mask Visualization,Keypoint Detection Model,Relative Static Crop,Crop Visualization,Background Subtraction,Circle Visualization,Multi-Label Classification Model,Text Display,Polygon Visualization,Background Color Visualization,Absolute Static Crop,Single-Label Classification Model,Instance Segmentation Model,Image Blur,Polygon Visualization,Contrast Equalization,Grid Visualization,Icon Visualization,Triangle Visualization - outputs:
Object Detection Model,Perspective Correction,SAM 3,S3 Sink,Stability AI Inpainting,Email Notification,Keypoint Detection Model,Morphological Transformation,Path Deviation,Qwen-VL,Clip Comparison,SAM 3,Line Counter,Twilio SMS/MMS Notification,QR Code Generator,OpenRouter,YOLO-World Model,Model Monitoring Inference Aggregator,OpenAI,Llama 3.2 Vision,Line Counter,Time in Zone,MoonshotAI Kimi,Stitch OCR Detections,Polygon Zone Visualization,Image Threshold,Anthropic Claude,OpenAI-Compatible LLM,OpenAI,Dynamic Crop,Detections Consensus,Size Measurement,Heatmap Visualization,Email Notification,Keypoint Visualization,Llama 3.2 Vision,Anthropic Claude,Stability AI Image Generation,Seg Preview,Google Vision OCR,Cache Set,Label Visualization,SAM 3,Instance Segmentation Model,Path Deviation,Bounding Box Visualization,Local File Sink,Depth Estimation,Google Gemini,CLIP Embedding Model,Multi-Label Classification Model,Polygon Visualization,Google Gemma API,Background Color Visualization,Qwen 3.6 API,Instance Segmentation Model,Qwen 3.5 API,Google Gemini,Polygon Visualization,Image Blur,Moondream2,SIFT Comparison,Per-Class Confidence Filter,Anthropic Claude,Florence-2 Model,Triangle Visualization,Time in Zone,Single-Label Classification Model,Roboflow Custom Metadata,OpenAI,Slack Notification,OpenAI,Instance Segmentation Model,LMM For Classification,Image Preprocessing,Roboflow Dataset Upload,Line Counter Visualization,Detections Classes Replacement,Segment Anything 2 Model,Stability AI Outpainting,Corner Visualization,Cache Get,Halo Visualization,LMM,Roboflow Dataset Upload,Time in Zone,Semantic Segmentation Model,Color Visualization,Google Gemini,Classification Label Visualization,Perception Encoder Embedding Model,Distance Measurement,Morphological Transformation,Trace Visualization,Detections Stitch,Stitch OCR Detections,Reference Path Visualization,Halo Visualization,Ellipse Visualization,Model Comparison Visualization,Dot Visualization,PTZ Tracking (ONVIF),Mask Visualization,Pixel Color Count,GLM-OCR,Crop Visualization,CogVLM,Circle Visualization,Text Display,Florence-2 Model,Contrast Equalization,Roboflow Vision Events,Webhook Sink,Icon Visualization,Twilio SMS Notification,MoonshotAI Kimi,Google Gemma
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Qwen3.5-VL in version v1 has.
Bindings
-
input
images(image): The image to infer on..model_version(roboflow_model_id): The Qwen3.5-VL model to be used for inference..
-
output
parsed_output(dictionary): Dictionary.thinking(string): String value.
Example JSON definition of step Qwen3.5-VL in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/qwen3_5vl@v1",
"images": "$inputs.image",
"prompt": "What is in this image?",
"model_version": "qwen3_5-0.8b",
"system_prompt": "You are a helpful assistant.",
"enable_thinking": "<block_does_not_provide_example>",
"max_new_tokens": "<block_does_not_provide_example>"
}