We solve the most boring problems for PDF imports, the edge cases that the frontier models miss.
Waking resume-fusion-1…
One import at a time · nothing stored
Resume Fusion 1
Resume Fusion 1 is our first fusion LLM, fine-tuned for one trick: importing resumes. It does it exactly, in about a second and for a fraction of a cent: every line where your PDF put it.
01 / Try it
Your PDF on the left. On the right, agent-native HTML in a human-friendly editor, just like Docs or Word, at the same scale.
or pick a sample
02 / How it works
Resume Fusion 1 is an LLM trained for a single job: understanding a resume and writing it back as HTML, exactly.
Resume Fusion 1 takes in the PDF itself, not a screenshot of it: every word, its font, its size and where it sits on the page.
It reads a resume the way a recruiter does: the name, the contact line, the sections, each role with its dates, and the bullets under it.
It answers in plain HTML: paragraphs, lists and rows that any agent can read, reason about and rewrite.
Before it answers, every line is checked against your PDF, so each one sits exactly where the PDF put it.
The HTML opens in a human-friendly editor, just like Docs or Word, looking exactly like the PDF it came from.
03 / The boring problems
Every resume hides a few. General-purpose frontier models trip on them; Resume Fusion 1 was fine-tuned on them.
04 / Developers
The API answers with Resume Fusion 1's agent-native HTML; the open-source editor opens it exactly as the PDF looked.
$ curl -F file=@resume.pdf \ https://api.theboringpdfcompany.com/v1/import { "html": "<div data-lbd=…", "paper": "letter", "margins": { … }, "pages": 1, "findings": {}, "model": "resume-fusion-1" }
Send a PDF; Resume Fusion 1 answers in about a second with agent-native HTML, its paper and its margins.
$ curl -F file=@resume.pdf https://api.theboringpdfcompany.com/v1/importimport { DocumentCanvas, Toolbar, useDocumentEditor } from '@boringpdf/editor'; const session = useDocumentEditor({ html, margins, paper, }); <Toolbar editor={session.editor} /> <DocumentCanvas session={session} />
The editor your users edit in, just like Docs or Word: React and Tiptap, every font a resume needs, open source. GitHub ↗
$ npm install @boringpdf/editorAdd PDF resume import to this app with The Boring PDF Company.
1. Import: POST the PDF as multipart field "file" to …/v1/import …
One paste into Claude Code, Cursor or any coding agent, and it wires up both halves.
05 / Benchmarks
A resume PDF in, agent-native HTML out, measured per import the same way for every model. Placeholder numbers until the runs are in.
Latency
1.4s
5.9× faster than the next fastest, Claude Haiku 5.5
Cost
$0.005
2.4× cheaper than the next cheapest, DeepSeek V4.1 Flash; 126× cheaper than Claude Opus 5.5
Fidelity
98.6%
20.2 points over the next best, Claude Opus 5.5
Turns
1 call
7× fewer model calls than the next best, Claude Opus 5.5
Seconds per import · Lower is better
US dollars per import · Lower is better
Lines placed exactly where the PDF put them · Higher is better
Model calls per import · Lower is better
Lines placed exactly · US dollars per import, log scale
Most attractive quadrant: cheaper and more exact than the median model
Cost per import (USD, log scale)
Fidelity is our own benchmark: the share of a resume's lines the HTML puts exactly where the PDF did. Cost is what an import costs the caller; ours is the Scaleup price. Turns: resume-fusion-1 answers in one call, where a frontier model looks at the page, writes HTML, looks again and corrects. Bars sort lowest to highest.
06 / Pricing
The editor is free and open source. The API is priced by the resume, from half a cent an import.
$49 / month
For a product shipping resume import.
$499 / month
For imports at the heart of the product.
Custom
For your cloud, your documents, your terms.