> ## Documentation Index
> Fetch the complete documentation index at: https://docs.moxus.cloud/llms.txt
> Use this file to discover all available pages before exploring further.

# Multimodal modules

> Moxus AI multimodal modules cover image understanding, image generation, PDF files, and Markdown files.

Moxus AI brings common multimodal workflows into one API gateway. You can call text, image, and document-processing models with the same account, API key, billing, and usage logs.

<Info>
  Multimodal availability depends on the selected model and API key restrictions. Check model capability labels in the model catalog before calling a model.
</Info>

<Columns cols={2}>
  <Card title="Image understanding" icon="image">
    Read images for descriptions, recognition, comparisons, extraction, and visual QA.
  </Card>

  <Card title="Image generation" icon="wand-sparkles">
    Generate images from prompts or edit existing images with supported models.
  </Card>

  <Card title="PDF files" icon="file-text">
    Use documents for summarization, QA, field extraction, and structured output.
  </Card>

  <Card title="Markdown files" icon="file-code">
    Add README files, docs, changelogs, and notes as text context in Conversation or API calls.
  </Card>
</Columns>

## How to choose a module

Start from the input type. Use image understanding for pictures and screenshots, image generation for visual creation, PDF files for document workflows, and Markdown files for readable text documents such as README files, notes, and changelogs. When you need predictable downstream data, combine the module with structured output.

## Markdown files

Conversation supports direct `.md` and `.markdown` uploads. In API calls, read the Markdown content and place it in `messages.content`; the model receives it as normal text context.

<Tip>
  Markdown content counts as input tokens. For long files, keep headings, lists, and important code blocks, and remove unrelated logs or repeated sections.
</Tip>

## Next steps

* [Vision and image generation](/en/guide/vision-and-image)
* [Markdown files](/en/overview/modules/markdown-files)