OCRRouter

Unlimited OCR vs MiniCPM-V 4.5

Pick Unlimited OCR for long reports and books that you want parsed in one request, with Markdown and bounding boxes out. Pick MiniCPM-V 4.5 for on-device or single-GPU OCR and document Q&A, where you want quantized builds and an Apache-2.0 licence. The main split is that Unlimited OCR is a layout-aware document parser with page boxes, while MiniCPM-V 4.5 is a general vision language model with no coordinates.

Unlimited OCRbaidu/unlimited-ocrMiniCPM-V 4.5openbmb/minicpm-v
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.2 s / page2.5 s / page
Best forBooks and very long documentsOCR on edge devices
InputsPDF, imagesimages
Languages30+ languages30+ languages
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
Math✓ YesNo
Bounding boxes✓ YesNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ 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 Unlimited OCR if

  • It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go through in one request.
  • It returns block types and bounding boxes alongside text, which you need for layout-aware extraction.
  • Baidu Cloud offers a hosted endpoint, so you can avoid running GPUs yourself if you want to.

Choose MiniCPM-V 4.5 if

  • It ships int4, GGUF and AWQ builds for llama.cpp and vLLM, which suits on-device, edge and single-GPU use.
  • It is a general vision language model, so you can ask questions about a document locally and get plain text, Markdown or JSON back.
  • Its Apache-2.0 weights and code leave you free to use it commercially.

Key differences

Unlimited OCRMiniCPM-V 4.5
Model type3B Mixture-of-Experts document parser from Baidu, derived from DeepSeek-OCR8.7B general vision language model from OpenBMB, built on Qwen3-8B and SigLIP2-400M
LicenceMITApache-2.0
How you run itSelf-host with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud's OCR productSelf-host only, with llama.cpp, vLLM, Ollama or Transformers; no hosted SLA
OutputMarkdown, plain text and bounding boxesPlain text, Markdown and JSON; no bounding box or layout output
Multi-page input40+ pages in one pass; context capped at 32,768 tokens and multi-page input only works in base modeNot published
HardwareNVIDIA GPU with CUDA 12.9 or 13.0; version 2 runs out of memory under SGLang on 12 GB GPUs; no CPU-only useQuantized int4, GGUF and AWQ builds; no int4 VRAM figure published
Known failureText repetition and looping on some pages, reports of hallucinated text, and formatting such as bold and italic mostly lostBenchmark scores are given only as images on the model card, so they are hard to verify

Sources

What each one is

Unlimited OCR

Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.

Unlimited OCR 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": "baidu/unlimited-ocr","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Unlimited OCR alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026