OCRmyPDF vs MiniCPM-V 4.5
Pick OCRmyPDF to make scanned PDF archives searchable as PDF/A on CPU-only machines. Pick MiniCPM-V 4.5 when you need Markdown or JSON text from documents, or local document Q&A on a single GPU. The main split is that OCRmyPDF adds a Tesseract text layer to the PDF, while MiniCPM-V 4.5 is an 8.7B vision language model that reads the page and returns text.
OCRmyPDFocrmypdf/ocrmypdf | MiniCPM-V 4.5openbmb/minicpm-v | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 1 credit / page | 2 credits / page |
| Per 1,000 pages | $1.00 | $2.00 |
| Typical speed | 1.0 s / page | 2.5 s / page |
| Best for | Searchable PDFs from scans | OCR on edge devices |
| Inputs | PDF, images | images |
| Languages | 100+ languages (via Tesseract) | 30+ languages |
| Max pages per request | 1,000 | 500 |
| Tables | No | ✓ Yes |
| Handwriting | No | ✓ Yes |
| Math | No | No |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose OCRmyPDF if
- You need validated searchable PDF/A output for archiving, and the OCR layer is inserted without re-encoding other content where possible.
- You only have CPUs, and you want work spread across all cores.
- You need Tesseract's 100+ languages through language packs.
Choose MiniCPM-V 4.5 if
- You want Markdown or JSON output, which OCRmyPDF does not produce.
- You want on-device or edge OCR using int4, GGUF or AWQ quantized builds on llama.cpp or vLLM.
- You want to ask questions about documents locally on a single GPU, under Apache-2.0 weights and code.
Key differences
| OCRmyPDF | MiniCPM-V 4.5 | |
|---|---|---|
| What it is | Command-line tool that adds a Tesseract OCR text layer to scanned PDFs | 8B open-weight vision language model from OpenBMB, built on Qwen3-8B and SigLIP2-400M |
| Licence | MPL-2.0 | Apache-2.0 |
| Hardware | CPU only, uses all CPU cores | Self-hosted with llama.cpp, vLLM, Ollama or Transformers; no int4 VRAM figure published |
| Output formats | Searchable PDF (PDF/A by default) and plain text | Plain text, Markdown and JSON |
| Layout and coordinates | No layout, table or Markdown output | No bounding box or layout output |
| Benchmarks | Not published | OpenBMB claims leading OCRBench results and state of the art PDF parsing on OmniDocBench, but the scores are given only as images |
| Known failure | --skip-text with default PDF/A output removes form fields (issue #1790); some PDFs with shared form Resources hang (issue #1763) | Ollama and SGLang support were still pending official releases on the model card |
Sources
- OCRmyPDF GitHub README
- OCRmyPDF docs
- Issue #1790 form fields
- Hugging Face model card
- MiniCPM-V 4.5 paper
What each one is
OCRmyPDF
Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.
OCRmyPDF detailsMiniCPM-V 4.5
8B vision model from OpenBMB (August 2025) built to run on devices, with strong OCR and document parsing.
MiniCPM-V 4.5 detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "ocrmypdf/ocrmypdf","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
OCRmyPDF alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026