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

# Multimodal

> Attach images for vision-capable models, or documents for any model.

Your prompt does not have to be just text. You can attach a picture or a document with the `--file` flag and ask about it. The two work differently, and which one you get depends on what you attach.

<CardGroup cols={2}>
  <Card title="Image Input" icon="image" href="/plugin/features/multimodal/image-input">
    Attach a picture and a vision-capable model reads it: describe a screenshot, transcribe a receipt, read a chart.
  </Card>

  <Card title="Documents" icon="file-lines" href="/plugin/features/multimodal/pdf-input">
    Attach a PDF or office file. Nito parses it to text so any model can reason over it.
  </Card>
</CardGroup>

## Images and Documents

| You attach | How it is handled | Model requirement |
| :- | :- | :- |
| An image (PNG, JPEG, and similar) | Sent to the model to look at | A vision-capable model |
| A document (PDF, DOCX, PPTX, XLSX, XLS, text) | Parsed to text before the model runs | Any model |

The practical rule: a picture needs a model that can see, while a document works with any model because it becomes text first. If you attach an image to a model that cannot accept images, Nito tells you clearly rather than guessing. See [Image Input](/plugin/features/multimodal/image-input) for that behavior, and [Document Parsing](/plugin/features/server-side-tools/file-parser) for how files are read.

Attach a file with `--file` on [`ask`](/plugin/commands/ask-and-continue) (it is repeatable), in a [`session`](/plugin/commands/session), or from the [terminal](/plugin/cli/ask-and-fusion-from-terminal).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.