> 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/qwen2-5-vl.md).

# Qwen2.5-VL

{% hint style="warning" %}
**Deprecated**

Use the unified Qwen-VL block (`roboflow_core/qwen_vlm@v1`), which exposes Qwen 2.5 VL alongside other Qwen variants and the OpenRouter passthrough.
{% endhint %}

This workflow block runs Qwen2.5-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/qwen25vl@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..                                                                                                                | ❌    |
| `prompt`        | `str`    | Optional text prompt to provide additional context to Qwen2.5-VL. Otherwise it will just be a default one, which may affect the desired model behavior.. | ❌    |
| `model_version` | `str`    | The Qwen2.5-VL model to be used for inference..                                                                                                          | ✅    |
| `system_prompt` | `str`    | Optional system prompt to provide additional context to Qwen2.5-VL..                                                                                     | ❌    |

The **Refs** column marks possibility to parametrise the property with dynamic values available in `workflow` runtime. See *Bindings* for more info.

### :material-shield-half-full:{ style="color: #5e6c75" } Runtime compatibility

:material-shield-alert:{ style="color: #d32f2f" } `hard` - runtime `self_hosted_cpu`; execution `local` : Requires a GPU; run\_locally() loads a model that needs CUDA.

### Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds `Qwen2.5-VL` in version `v1` has.

<details>

<summary>Input and output bindings</summary>

* input
  * `images` ([*`image`*](https://inference.roboflow.com/workflows/kinds/image/)): The image to infer on..
  * `model_version` ([*`roboflow_model_id`*](https://inference.roboflow.com/workflows/kinds/roboflow_model_id/)): The Qwen2.5-VL model to be used for inference..
* output
  * `parsed_output` ([`dictionary`](https://inference.roboflow.com/workflows/kinds/dictionary/)): Dictionary.

</details>

<details>

<summary>Example JSON definition</summary>

```json
{
	    "name": "<your_step_name_here>",
	    "type": "roboflow_core/qwen25vl@v1",
	    "images": "$inputs.image",
	    "prompt": "What is in this image?",
	    "model_version": "qwen25-vl-7b",
	    "system_prompt": "You are a helpful assistant."
	}
```

</details>