# Multimodal Input

Infron AI supports multiple input modalities beyond text, allowing you to send images, PDFs, and audio files to compatible models through our unified API. This enables rich multimodal interactions for a wide variety of use cases.

## Supported Modalities

### Images

Send images to vision-capable models for analysis, description, OCR, and more. Infron AI supports multiple image formats and both URL-based and base64-encoded images.

[Learn more about image inputs →](https://infronai.gitbook.io/docs/features/multimodal-input/images-inputs)

### PDFs

Process PDF documents with any model on Infron AI. 

Learn more about PDF processing →

### Audio

Send audio files to speech-capable models for transcription, analysis, and processing. 

Learn more about audio inputs →

## Getting Started

All multimodal inputs use the same `/v1/chat/completions` endpoint with the `messages` parameter. Different content types are specified in the message content array:

* **Images**: Use `image_url` content type
* **PDFs**: Use `file` content type with PDF data
* **Audio**: Use `input_audio` content type

You can combine multiple modalities in a single request, and the number of files you can send varies by provider and model.

## Model Compatibility

{% hint style="info" %}
Not all models support every modality. 
{% endhint %}

* **Vision models**: Required for image processing
* **File-compatible models**: Can process PDFs natively or through our parsing system
* **Audio-capable models**: Required for audio input processing

Use our [Models page](https://app.onerouter.pro/models) to find models that support your desired input modalities.

## Input Format Support

Infron AI supports both **direct URLs** and **base64-encoded data** for multimodal inputs:

#### URLs (Recommended for public content)

* **Images**: `https://example.com/image.jpg`
* **PDFs**: `https://example.com/document.pdf`
* **Audio**: Not supported via URL (base64 only)

### Base64 Encoding (Required for local files)

* **Images**: `data:image/jpeg;base64,{base64_data}`
* **PDFs**: `data:application/pdf;base64,{base64_data}`
* **Audio**: Raw base64 string with format specification

URLs are more efficient for large files as they don't require local encoding and reduce request payload size. 

Base64 encoding is required for local files or when the content is not publicly accessible.