Keep editing your documents
Use extracted text, headings, and tables for notes, research summaries, and content creation, with less reformatting and manual transcription.
MinerU Online · No install, open and go
Convert PDFs, papers, and web pages into clean Markdown, HTML, and structured JSON. Tuned for scientific layouts, chemical formulas, and complex tables — built for AI agents and RAG pipelines.
Figure 2. Structure of compound 3a
PDF / DOCX / PPTX / XLSX / HTML / PNG
files up to 10 MB · images up to 5 MB · PDFs up to 5 pages Upgrade to Pro
Your documents and results belong to your account.
Sign inReal parsing examples
From chemical structures, mathematical formulas, and complex tables to handwritten notes, academic papers, A3 exam papers, and more — 100% extraction and reconstruction.
Compare molecular structures and accompanying text in the original document and parsing result side by side.
From organizing your reading to integrating applications, choose the output format that moves your work forward.
Use extracted text, headings, and tables for notes, research summaries, and content creation, with less reformatting and manual transcription.
Connect structured results to knowledge bases, search systems, and AI workflows for programmatic access and further processing.
Export to Word or HTML to keep editing a document or present its content on the web.
Use recognized mathematical formulas in papers, teaching materials, and technical documents with less manual re-entry.
Capabilities
Beyond text extraction. MinerU understands the structure, semantics, and hierarchy of scientific layouts.
01 / SCIENCE
Purpose-built for chemical formulas, mathematical notation, complex tables, and multi-column layouts — preserving reading order and logical structure.
02 / AGENTS
Structured JSON with semantic tags for headings, paragraphs, tables, figures, and formulas — plug directly into RAG, knowledge bases, and agent workflows.
03 / SPEED
Elastic cloud scheduling parses hundred-page documents in seconds, while batch jobs run in parallel to meet enterprise throughput.
Who uses MinerU
From one person's reading list to an organisation-wide knowledge base, MinerU sits at the first gate where documents enter your systems.

Researchers
Turn papers, patents, and lab notes into searchable structured text in bulk. Formulas and chemical notation survive intact, so literature reviews stop being manual transcription.

Developers
One line of code. Get semantically tagged JSON straight into your RAG pipeline, knowledge base, or agent workflow — no parsing pipeline of your own to maintain.

Enterprise
Batch-ingest research reports, contracts, and archives. Pair it with on-premise deployment and usage reporting to make document assets genuinely searchable.
API reference
A RESTful API and multi-language SDKs cover upload, status, and download — with clear error codes and webhooks so integration stays painless.
import os
import time
import requests
API = "https://YOUR_API_HOST/api/open/v1"
headers = {"Authorization": "Bearer " + os.environ["MINERU_API_KEY"]}
with open("paper.pdf", "rb") as source:
response = requests.post(API + "/tasks", headers=headers,
files={"file": ("paper.pdf", source, "application/pdf")},
data={"is_ocr": "false"}, timeout=120)
response.raise_for_status()
body = response.json()
if body["code"] != 0:
raise RuntimeError(body["msg"])
task_id = body["data"]["task_id"]
print("Task:", task_id)
deadline = time.monotonic() + 1800
while time.monotonic() < deadline:
response = requests.get(API + "/tasks/" + task_id, headers=headers, timeout=30)
response.raise_for_status()
body = response.json()
if body["code"] != 0:
raise RuntimeError(body["msg"])
data = body["data"]
if data["task"]["status"] == "completed":
with requests.get(data["results"]["full_zip_url"], stream=True, timeout=120) as result:
result.raise_for_status()
with open("result.zip", "wb") as output:
for chunk in result.iter_content(1024 * 1024):
output.write(chunk)
break
if data["task"]["status"] in {"failed", "expired"}:
raise RuntimeError(data["task"]["error"] or data["task"]["status"])
time.sleep(3)
else:
raise TimeoutError("Continue querying task " + task_id)Find quick answers about file formats, recognition results, and how to use MinerU.
General document parsing supports PDF, Word, PPT, Excel, HTML, and images including PNG, JPG, WebP, GIF, BMP, and TIFF. Chemical structure recognition supports PDF and images. See the workbench and plan details for file limits.
You can upload scanned PDFs or images of notes. The handwriting example shows Chinese text, mathematical symbols, and formulas. Results depend on handwriting, clarity, and photo quality, so compare key content with the original.
General document parsing supports Markdown, JSON, HTML, Word (DOCX), and LaTeX. Chemical structure recognition provides JSON results. Available exports are shown on the corresponding task page.
Switching export formats for the same task does not repeat parsing or charge you again. Export the formats you need within the result retention period.
Results are kept for 7 days. Download the files you need before they expire; after expiration, viewing and downloading are no longer available.
Use the website to upload, view, and export documents directly. Use the API to integrate parsing into your applications or automated workflows. Free includes website access; Pro monthly and annual plans include API access.
Pricing
Online parsing and all five export formats. Choose the plan that fits your documents.
Sign up and start right away
$0/ month
No payment method required
Flexible access, one month at a time
$9.90/ month
USD · one-time payment
A full year at a lower price
$59.90/ year
USD · one-time payment
Pro also includes the daily free allowance. Monthly pages reset each month and do not accumulate. Outputs are retained for 7 days.
On-premise
For finance, healthcare, government, and research institutions, MinerU deploys fully on-premise: models and data run entirely inside your own network.

Leave repetitive transcription to the tools. Save your time for reading, research, and creation.