> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen-vl.md).
# Qwen-VL
Run any Qwen vision-language model - natively on Roboflow infrastructure or 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
#### 🛠️ Backend selection
* **Native (Roboflow)** - small Qwen-VL models (0.8B–7B) run on the same infrastructure as your other Roboflow models. Lower latency. Recommended for tasks like OCR, captioning, and visual question answering.
* **OpenRouter** - large hosted Qwen models (9B–397B) reached via [OpenRouter](https://openrouter.ai/). Defaults to a Roboflow-managed API key and bills your Roboflow credits. Paste your own `sk-or-...` key in the `api_key` field to bypass Roboflow billing. Recommended for structured tasks that benefit from larger models (classification, object-detection, structured-answering).
The `model_version` dropdown lists every supported variant; each is bound to one backend. A validator catches mismatches between your selected backend and model.
#### 🔒 Privacy filter (OpenRouter only)
* **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.
### Type identifier
Use the following identifier in step `"type"` field: `roboflow_core/qwen_vlm@v1` to add the block as a step in your workflow.
### Properties
| **Name** | **Type** | **Description** | Refs |
| -------------------------- | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- |
| `name` | `str` | Enter a unique identifier for this step.. | ❌ |
| `api_key` | `str` | OpenRouter API key (only used when backend=openrouter). Defaults to Roboflow's managed key. Provide your own `sk-or-...` key to call OpenRouter directly without Roboflow billing.. | ✅ |
| `privacy_level` | `str` | Provider privacy filter (only used when backend=openrouter). 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` | Sampling temperature (only used when backend=openrouter). The native Qwen-VL runtime doesn't accept a temperature knob. Range 0.0-2.0 - higher = more random / "creative" generations.. | ✅ |
| `max_concurrent_requests` | `int` | Maximum number of OpenRouter requests to run in parallel for a batch of images (only used when backend=openrouter). The native backend processes images sequentially. If unset, falls back to the global Workflows Execution Engine default. Restrict this if you hit OpenRouter rate limits.. | ❌ |
| `backend` | `str` | Where to run inference. Native = Roboflow infrastructure. OpenRouter = large hosted Qwen models via OpenRouter.. | ❌ |
| `model_version` | `str` | Native Qwen-VL variant. Pick a pre-trained model or `Fine-tuned model` to use a Qwen3 fine-tune from your workspace.. | ✅ |
| `fine_tuned_model_id` | `str` | Fine-tuned Qwen3-VL model from your workspace, in `workspace/version` form.. | ✅ |
| `openrouter_model_version` | `str` | OpenRouter-hosted Qwen variant.. | ✅ |
| `task_type` | `str` | Task type to be performed by model. Value determines required parameters and output response.. | ❌ |
| `prompt` | `str` | Text prompt to the Qwen model. | ✅ |
| `enable_thinking` | `bool` | Enable Qwen3.5-VL's reasoning mode, where the model emits thinking tokens before its answer. The reasoning trace is returned in the `thinking` output. Only the Qwen 3.5 VL 2B checkpoint (and Qwen3-VL fine-tunes derived from it) supports this; ignored elsewhere.. | ❌ |
| `output_structure` | `Dict[str, str]` | Dictionary with structure of expected JSON response. | ❌ |
| `classes` | `List[str]` | List of classes to be used. | ✅ |
The **Refs** column marks possibility to parametrise the property with dynamic values available in `workflow` runtime. See *Bindings* for more info.
### Runtime compatibility
`requires_internet` - air-gapped / offline deployments : This block depends on a service that is not reachable from fully offline / air-gapped deployments.
### Input and Output Bindings
The available connections depend on its binding kinds. Check what binding kinds `Qwen-VL` in version `v1` has.
Input and output bindings
* input
* `api_key` (*Union\[*[*`ROBOFLOW_MANAGED_KEY`*](/workflows/developer-guide/developer-guide/kinds/roboflow-managed-key.md)*,* [*`secret`*](/workflows/developer-guide/developer-guide/kinds/secret.md)*,* [*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)*]*): OpenRouter API key (only used when backend=openrouter). Defaults to Roboflow's managed key. Provide your own `sk-or-...` key to call OpenRouter directly without Roboflow billing..
* `temperature` ([*`float`*](/workflows/developer-guide/developer-guide/kinds/float.md)): Sampling temperature (only used when backend=openrouter). The native Qwen-VL runtime doesn't accept a temperature knob. Range 0.0-2.0 - higher = more random / "creative" generations..
* `images` ([*`image`*](/workflows/developer-guide/developer-guide/kinds/image.md)): The image to infer on..
* `model_version` ([*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)): Native Qwen-VL variant. Pick a pre-trained model or `Fine-tuned model` to use a Qwen3 fine-tune from your workspace..
* `fine_tuned_model_id` (*Union\[*[*`roboflow_model_id`*](/workflows/developer-guide/developer-guide/kinds/roboflow-model-id.md)*,* [*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)*]*): Fine-tuned Qwen3-VL model from your workspace, in `workspace/version` form..
* `openrouter_model_version` ([*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)): OpenRouter-hosted Qwen variant..
* `prompt` ([*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)): Text prompt to the Qwen model.
* `classes` ([*`list_of_values`*](/workflows/developer-guide/developer-guide/kinds/list-of-values.md)): List of classes to be used.
* output
* `output` (*Union\[*[*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)*,* [*`language_model_output`*](/workflows/developer-guide/developer-guide/kinds/language-model-output.md)*]*): String value if `string` or LLM / VLM output if `language_model_output`.
* `classes` ([`list_of_values`](/workflows/developer-guide/developer-guide/kinds/list-of-values.md)): List of values of any type.
* `thinking` ([`string`](/workflows/developer-guide/developer-guide/kinds/string.md)): String value.
Example JSON definition
```json
{
"name": "",
"type": "roboflow_core/qwen_vlm@v1",
"api_key": "rf_key:account",
"privacy_level": "",
"max_tokens": "",
"temperature": "",
"max_concurrent_requests": "",
"images": "$inputs.image",
"backend": "",
"model_version": "Qwen 3.5 VL 2B",
"fine_tuned_model_id": "your-workspace/3",
"openrouter_model_version": "Qwen 3.6 27B",
"task_type": "",
"prompt": "my prompt",
"enable_thinking": "",
"output_structure": {
"my_key": "description"
},
"classes": [
"class-a",
"class-b"
]
}
```