> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://hiddenlayer.ferndocs.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://hiddenlayer.ferndocs.com/_mcp/server.

# 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        |