Skip to content
mineru-runpod
Blog
PDF transformed to Markdown by a serverless cloud

Deploy
MinerU 2.5 Pro
on RunPod
in two clicks

Open-source RunPod Serverless template. Self-hosted endpoint, scales to zero, ~$0.001 per warm page on a 24 GB RTX 4090.
Get started GitHub MinerU model card

How it works

Section titled “How it works”

This is an open-source repo and RunPod Hub template — not a hosted service. Fork it, deploy from the Hub, and the worker runs on your RunPod account against your wallet.

Under the hood it’s one Docker image wrapping MinerU (3.2.x runtime, MinerU2.5-Pro-2605-1.2B VLM by default). Send a PDF as a URL, base64 blob, or path on a mounted volume. Get back Markdown, a structured content_list, the raw middle.json, and extracted images. When traffic stops, RunPod tears the worker down in seconds.

What you get

Section titled “What you get”

State-of-the-art accuracy

The 1.2B MinerU VLM tops OmniDocBench for text, tables, formulas, and reading order. Combined with the pipeline backend, 109 languages of OCR, handwriting included.

Pay per second, not per hour

idle_timeout=10 + FlashBoot means a 100-page doc lands for about $0.03 on a 24 GB RTX 4090. No worker running? No bill.

No glue code

Deploy from the Hub in one click, or fork and let RunPod auto-build your copy. Either way: ten minutes from sign-up to first parse.

Safe to ship

Apache 2.0 with clear commercial thresholds (100M MAU, $20M revenue). The cleanest open license in the GPU-PDF space.

Try it in 30 seconds

Section titled “Try it in 30 seconds”
from mineru_client import MineruClient


client = MineruClient(endpoint_id="<your-endpoint-id>")
result = client.parse_document(file_url="https://example.com/report.pdf", end_page=4)
client.save_tarball(result, "./out/doc")
# → markdown + content_list + middle.json + images

Pick your starting point

Section titled “Pick your starting point”

How it's built

Architecture, what’s in the repo, supported workloads, and how it compares to Marker, GROBID, and Nougat.

Read the overview

Deploy in 10 minutes

Sign up for RunPod, deploy mineru-runpod from the Hub, paste the endpoint id, parse your first PDF.

Sign up for RunPod

Pick the right GPU

When 24 GB is enough, when to jump to 48 GB, and which RunPod pool IDs map to which workload shapes. Includes the official MinerU hardware compatibility table.

Choosing a GPU

When something breaks

Hub build flakes, Blackwell crashes, Latin-on-Cyrillic, OOM, cold starts. How to read the debug block to diagnose anything else.

Troubleshooting