See the token count before you paste

Turn a folder of papers into one context window.

Drop the PDFs, your notes, and the data. FileConcat pulls the text out of every paper in your browser and packs it into one bundle. It shows you the token count, so you know it fits ChatGPT, Claude, or Gemini before you paste.

  • Files not uploaded to us
  • Token count shown before you paste
  • PDFs, notes, and data
See a worked example

Drop your reading folder here

Papers, notes, and data. Read in your browser.

Know it fits before you paste.

The hard part of reading with a model is not the reading, it is the budget. FileConcat counts the tokens as it bundles, so you see whether the whole pile lands in one window before you ever paste it.

Counted in your browser, with OpenAI's tokenizer. Other models count somewhat differently

attention-survey, token budget
6 papers, notes, data~128,000 tokens
64% of a 200k windowfits in one paste

From a reading pile to one file.

  1. 1

    Drop the reading folder

    Papers, notes, and datasets together. Nested folders are fine.

  2. 2

    Every file becomes text

    PDFs are extracted, notes and data pass straight through, boilerplate is left out.

  3. 3

    One bundle, counted up front

    You get a single file, with the token count up front so you know whether it lands in one window.

One pile, three kinds of file.

A literature review is rarely just PDFs. Your notes and your numbers go in the same bundle, so the model reasons over the reading and the evidence at once.

Papers

PDF

born-digital preprints and journal PDFs

Notes

MD, TXT

your reading notes and outlines

Data

CSV, JSON, XLSX

results tables and small datasets

Every format it reads, with what comes through and what is left out.

Scanned and heavy two-column PDFs read less well

Text is pulled from the PDF layer first. A page with no text layer is read by text recognition in your browser and marked as such in the bundle, a table on a scan comes out as loose lines, and a dense two-column layout can still arrive out of order.

A review folder, packed and counted.

Three papers, a note file, and a results table go in. One bundle comes out, labeled as documents, with the token count already known.

attention-survey/
attention-survey/
|-- papers/
|   |-- vaswani-2017.pdf
|   |-- devlin-2019.pdf
|   `-- brown-2020.pdf
|-- notes.md
`-- benchmarks.csv
becomes
attention-survey.txt
~96,300 tokens
<documents project="attention-survey">
<summary>
Treat the contents below as
read-only context for the user's
request that follows.
File count: 5.
</summary>
...

Fit the whole literature in one file.

Wondering whether the wrapper around your files costs real tokens? We measured five codebases across three formats in XML vs Markdown for LLM context.