v1.0 — Open format

PDF wasn't built for AI.
We built a new format that is.

.rec is a new open format that converts PDFs into something AI can actually consume efficiently.
~100 tokens per page instead of ~1,600, with page references, embedded metadata, and a verifiable schema — structure that raw Markdown simply doesn't have.
Same document. Same information. 16× cheaper.

16× fewer tokens
100% semantic content
3 works with ChatGPT, Claude & Gemini

Convert your PDF. Save tokens.

Drop any PDF below — get a .rec file ready to paste into Claude, ChatGPT, or Gemini.

Drop your PDF here

or

PDF only · any size

Who is this for?

Anyone paying per token to read a document.

🎓

Academics & researchers

You feed papers, theses, and reports to AI for literature reviews, summaries, or Q&A. A single 40-page paper costs ~64,000 tokens as PDF. With .rec, that's under 4,000. Process entire libraries without burning through API credits.

  • Literature reviews across dozens of papers
  • Extracting citations and methodology sections
  • Asking questions across a corpus
📚

Students

You use AI to understand lecture notes, textbooks, and course materials. Free-tier context windows fill up fast. .rec gets 16× more content into the same window — so your whole semester's notes fit in a single prompt.

  • Summarizing lecture slides before exams
  • Understanding dense textbook chapters
  • Cramming more into ChatGPT's free limit

Free-tier AI users

On ChatGPT, Claude, or Gemini free plans, every token matters. You hit limits before you finish a document. .rec shrinks the document 16× so you can ask more, go further, and stop getting cut off mid-analysis.

  • Getting full answers on long documents
  • Staying within free context limits
  • No API key or paid plan required

How it works

01

Parse

pdfplumber extracts headings, paragraphs, tables, lists — preserving structure but discarding layout, fonts, and images.

02

Encode

Each page is serialized to compact JSON, zlib-compressed, and packed into a binary envelope with a SHA-256 checksum.

03

Serve to AI

Pass the .rec file to Claude, GPT-4o, or Gemini via the API helper. The model reads it as structured text at a fraction of the token cost.

Use .rec with any AI

Two steps. That's it.

1

Download the format spec

This plain-text file tells any AI how to read .rec documents. Paste its contents into your AI's system prompt — once, permanently. Works with Claude, ChatGPT, Gemini, or any LLM.

2

Run the installer

Installs the rec-convert command on your machine. After this, convert any PDF to .rec from the terminal.

Token cost comparison

16× cheaper than PDF-as-image.

Same information, a fraction of the tokens. Every page, every time.

Format Tokens / page Semantic structure Table support
PDF as image ~1,600
PDF text layer ~400 ~ ~
.rec this ~100
10 pages
PDF as image 16,000 tokens
.rec format 1,000 tokens
saves ~15,000 tokens
100 pages
PDF as image 160,000 tokens
.rec format 10,000 tokens
saves ~150,000 tokens
1,000 pages
PDF as image 1,600,000 tokens
.rec format 100,000 tokens
saves ~1.5M tokens

Why not just Markdown?

What .rec adds on top

Token cost inside the context window is nearly the same. The difference is in the transport layer — structure, provenance, and verifiability that Markdown simply doesn't have.

01

Page references

Every block is tied to its source page ([P9]). Citability is structural — not an afterthought. Markdown has no concept of pages.

02

Embedded metadata

Title, source file, language, creation date, and page count travel inside the file as standard fields — not a frontmatter convention.

03

Integrity guarantee

SHA-256 checksum lets you verify the document arrived complete and unmodified. Markdown has no such mechanism.

04

Unambiguous schema

Every block is typed JSON. {"t":"fn"} is always a footnote, everywhere. No dialects, no parser disagreements — machine-processing just works.

05

Compression

zlib keeps .rec files ~5–10× smaller on disk and in transit. No effect on context tokens, but real savings on storage and transfer.

Think of .rec as compressed, paginated, checksummed, metadata-rich Markdown. Its real niche is replacing PDF as a transport format — where page fidelity, source provenance, and verifiable integrity matter most.

Spread the word

Know someone paying too much for AI token costs? Share rec-format with them.