> 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/lmm-for-classification.md).

# LMM For Classification

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

This block is deprecated and may be removed in a future release.
{% endhint %}

Classify an image into one or more categories using a Large Multimodal Model (LMM).

You can specify arbitrary classes to an LMMBlock.

The LLMBlock supports two LMMs:

* OpenAI's GPT-4 with Vision.

You need to provide your OpenAI API key to use the GPT-4 with Vision model.

### Type identifier

Use the following identifier in step `"type"` field: `roboflow_core/lmm_for_classification@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..                                                                                  | ❌    |
| `lmm_type`       | `str`       | Type of LMM to be used.                                                                                                    | ✅    |
| `classes`        | `List[str]` | List of classes that LMM shall classify against.                                                                           | ✅    |
| `lmm_config`     | `LMMConfig` | Configuration of LMM.                                                                                                      | ❌    |
| `remote_api_key` | `str`       | Holds API key required to call LMM model - in current state of development, we require OpenAI key when `lmm_type=gpt_4v`.. | ✅    |

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.

`hard` - runtime `hosted_serverless`; execution `remote` : LMM\_ENABLED=False on Roboflow Hosted Serverless: the /llm\_v1 endpoint is not registered, so run\_remotely() returns 404.

### Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds `LMM For Classification` in version `v1` has.

<details>

<summary>Input and output bindings</summary>

* input
  * `images` ([*`image`*](/workflows/developer-guide/developer-guide/kinds/image.md)): The image to infer on..
  * `lmm_type` ([*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)): Type of LMM to be used.
  * `classes` ([*`list_of_values`*](/workflows/developer-guide/developer-guide/kinds/list-of-values.md)): List of classes that LMM shall classify against.
  * `remote_api_key` (*Union\[*[*`secret`*](/workflows/developer-guide/developer-guide/kinds/secret.md)*,* [*`string`*](/workflows/developer-guide/developer-guide/kinds/string.md)*]*): Holds API key required to call LMM model - in current state of development, we require OpenAI key when `lmm_type=gpt_4v`..
* output
  * `raw_output` ([`string`](/workflows/developer-guide/developer-guide/kinds/string.md)): String value.
  * `top` ([`top_class`](/workflows/developer-guide/developer-guide/kinds/top-class.md)): String value representing top class predicted by classification model.
  * `parent_id` ([`parent_id`](/workflows/developer-guide/developer-guide/kinds/parent-id.md)): Identifier of parent for step output.
  * `root_parent_id` ([`parent_id`](/workflows/developer-guide/developer-guide/kinds/parent-id.md)): Identifier of parent for step output.
  * `image` ([`image_metadata`](/workflows/developer-guide/developer-guide/kinds/image-metadata.md)): Dictionary with image metadata required by supervision.
  * `prediction_type` ([`prediction_type`](/workflows/developer-guide/developer-guide/kinds/prediction-type.md)): String value with type of prediction.

</details>

<details>

<summary>Example JSON definition</summary>

```json
{
	    "name": "<your_step_name_here>",
	    "type": "roboflow_core/lmm_for_classification@v1",
	    "images": "$inputs.image",
	    "lmm_type": "gpt_4v",
	    "classes": [
	        "a",
	        "b"
	    ],
	    "lmm_config": {
	        "gpt_image_detail": "low",
	        "gpt_model_version": "gpt-4o",
	        "max_tokens": 200
	    },
	    "remote_api_key": "xxx-xxx"
	}
```

</details>