Daily Dose of AITuesday

Is it cheaper to send a PDF to an LLM or extract the text first? (RAG question)

Is it cheaper to send a PDF to an LLM or extract the text first? (RAG question)

Extracting the text first is usually cheaper, because you send only text tokens. Sending the PDF directly usually costs more, since models like Claude, ChatGPT and Gemini also process each page as an image, but it keeps screenshots, charts and diagrams that text extraction loses.
A few days ago, while working on a RAG project, one simple question stopped me:
“What costs more — sending the PDF directly to an LLM, or extracting the text first?”
Sounds simple… but then came the next question: What if the PDF has screenshots, charts, or diagrams?
That took me down an interesting rabbit hole of how Claude, ChatGPT & Gemini process PDFs — and why cheaper input isn’t always the better choice.
Sharing what I learned in this visual
What would you choose for RAG — PDF or extracted text?
Ebooks to watch for--https://www.aiplaybookhub.com/books/genai-testing-for-qa.html

About the author

Sumit Chaudhary

Author of 9 practical eBooks on AI, QA and automation at AI Playbook Hub.

Keep learning

Go deeper with an eBook

AI Productivity

Build It with Claude Code

Learn Claude Code by building 6 real projects, from your first command to CI automation, with every feature explained the moment you use it.

  • 6 hands-on projects
  • 52 features explained in place
  • 32 interview Qs + 50-question mock
Automation

n8n for QA & SDET

Learn the 26 n8n nodes testers use most, then build 5 QA automation projects you can show on GitHub and LinkedIn.

  • 26 nodes with QA use cases
  • 5 step-by-step POC projects
  • 7-day build plan