# PDF Upload with Sonar API Questions

**URL:** <https://community.perplexity.ai/t/pdf-upload-with-sonar-api-questions/1255>\
**Category:** General\
**Tags:** sonar-api\
**Created:** [August 29, 2025, 11:36pm UTC](https://community.perplexity.ai/t/pdf-upload-with-sonar-api-questions/1255 "2025-08-29T23:36:48Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![JSK](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/jsk/32/187_2.png) [@JSK](https://community.perplexity.ai/u/JSK)\
**Post date:** [August 29, 2025, 11:36pm UTC](https://community.perplexity.ai/t/pdf-upload-with-sonar-api-questions/1255/1 "2025-08-29T23:36:48Z")

</div>

My questions relate to the functionality mentioned here:

> **[PDF Uploads with Sonar - Perplexity](https://docs.perplexity.ai/guides/pdf-uploads)**
>
> Learn how to upload and analyze PDF documents using Sonar models

The public URL requirement is unusual. On the above documentation page, a password protected PDF is mentioned, which makes sense given it would be on a public server. I can’t find any mention on how to supply the PDF password to the chat completions API?

Also, I just wanted to verify that I would be able to use chat completion structured output and that the PDF evaluation would be multi-modal (text and images)?

So three questions:

1. How do PDF passwords work with the chat completions API?

2. Does the PDF evaluation by Sonar also analyze images?

3. I assume I will be able to use your structured output to get the results in JSON format?