—
per month—per PDF
—input tokens/mo
—per year
Send the pages you need, not the whole PDF
Dumping entire documents into the model is easy and expensive. Retrieve the relevant pages first. For retrieval cost see the RAG chatbot cost calculator.
What it costs to run thousands of PDFs through an LLM.
Dumping entire documents into the model is easy and expensive. Retrieve the relevant pages first. For retrieval cost see the RAG chatbot cost calculator.
Free PDF-processing cost calculator — number of PDFs, pages and tokens to the LLM cost of processing them.
Cost per PDF = pages × tokens/page × input price + output tokens × output price. Feeding whole documents is input-heavy, so page count and how much you send drive the bill more than the answer length.
Don't send whole documents blindly — extract or retrieve only the relevant pages, chunk long PDFs, and cache repeated system prompts. Full-document input is the biggest, most avoidable cost.