OCRRouter

OpenOCR vs MiniCPM-V 4.5

Pick OpenOCR for self-hosted Chinese and English document parsing, especially academic PDFs with formulas, when you want a 0.1B model and bounding boxes. Pick MiniCPM-V 4.5 for local or on-device OCR and document Q&A on a single GPU, with quantized builds and Markdown or JSON output. The main split is size and output: OpenOCR is tiny and gives coordinates, MiniCPM-V is an 8.7B general vision language model with no layout or box output.

OpenOCRfudan/openocrMiniCPM-V 4.5openbmb/minicpm-v
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed0.5 s / page2.5 s / page
Best forLightweight OCR pipeline on CPUOCR on edge devices
InputsPDF, imagesimages
LanguagesChinese and English30+ languages
Max pages per request500500
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ Yes
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose OpenOCR if

  • It reports 90.57 on OmniDocBench v1.5 (OpenDoc-0.1B) with only 0.1B parameters, though the authors measured it themselves.
  • It returns bounding boxes and LaTeX, so you can get coordinates and formulas from academic PDFs.
  • UniRec-0.1B reads plain text and single or multi-line formulas in one model, and the toolkit supports ONNX export.

Choose MiniCPM-V 4.5 if

  • It runs on llama.cpp and vLLM with int4, GGUF and AWQ builds, which suits on-device or edge OCR.
  • It outputs Markdown and JSON, and works as a general model for local document Q&A on a single GPU.
  • It is not limited to Chinese and English by a stated language restriction, unlike OpenDoc and UniRec, and OpenBMB claims leading OCRBench results above GPT-4o-latest and Gemini 2.5.

Key differences

OpenOCRMiniCPM-V 4.5
Model size0.1B (OpenDoc-0.1B and UniRec-0.1B)8.7B, built on Qwen3-8B and SigLIP2-400M
LicenceApache-2.0Apache-2.0 for weights and code
How you run itSelf-host as a Python library, with ONNX exportSelf-host with llama.cpp, vLLM or Transformers; Ollama and SGLang support was still pending on the model card
Output formatsPlain text, LaTeX, bounding boxesPlain text, Markdown, JSON; no bounding box or layout output
LanguagesOpenDoc and UniRec support only Chinese and EnglishNot published
Benchmarks90.57 on OmniDocBench v1.5 (OpenDoc-0.1B), self-reportedClaims leading OCRBench and OmniDocBench PDF parsing results, but scores appear only as images on the model card
Known limitsDocument parsing needs a separate layout model, PP-DocLayoutV2 from PaddlePaddle; no hardware or throughput figuresNo int4 VRAM figure published; no hosted SLA

Sources

What each one is

OpenOCR

Fudan's open toolkit for text detection and recognition, formulas, tables and document parsing.

OpenOCR details

MiniCPM-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 details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "fudan/openocr","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

OpenOCR alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026