# Multi-Modal Models

Image models are not currently the primary use case expected to be protected by AI Runtime Security; however, we offer the option in multi-modal models to block image input if required.

## Modal Type: Vision/Image

| Environment Key | Required | Example Value | Description |
|  --- | --- | --- | --- |
| `HL_LLM_BLOCK_IMAGES_UPLOAD` | False | False | Flag to block uploading images. |


## Models Supported

| Model Provider / Cloud Model Service | Support Status |
|  --- | --- |
| Anthropic | Supported |
| Azure OpenAI | Unsupported |
| Gemini | Supported |
| Hugging Face TGI OpenAI | Unsupported |
| OpenAI | Supported |
| AzureML | Partial |
| AWS | Partial |