OCRRouter

GOT-OCR 2.0 vs MiniCPM-V 4.5

Pick GOT-OCR 2.0 for formulas, sheet music, chemical structures and region-specific OCR on English and Chinese documents. Pick MiniCPM-V 4.5 when you want a general vision language model with an Apache-2.0 licence on the weights and code, quantized builds for a single GPU or edge device, and document Q&A. The main split is scope: GOT-OCR 2.0 is a 580M specialist with special output formats, MiniCPM-V 4.5 is an 8.7B general model.

GOT-OCR 2.0stepfun/got-ocr-2MiniCPM-V 4.5openbmb/minicpm-v
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed1.5 s / page2.5 s / page
Best forFormatted text, formulas and chartsOCR on edge devices
Inputsimagesimages
LanguagesChinese, English30+ languages
Max pages per request100500
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 GOT-OCR 2.0 if

  • You need LaTeX, TikZ, SMILES or kern output for formulas, chemical structures or sheet music.
  • You want to OCR one region of a page, guided by box coordinates or color.
  • You want a small 580M model with multi-page OCR and batched inference in Hugging Face Transformers.

Choose MiniCPM-V 4.5 if

  • You want Apache-2.0 on both weights and code, with no non-commercial training data licence to check.
  • You need quantized builds (int4, GGUF, AWQ) that run on llama.cpp or vLLM for on-device or single-GPU use.
  • You want to ask questions about documents locally and get Markdown or JSON back, not only transcribe them.

Key differences

GOT-OCR 2.0MiniCPM-V 4.5
LicenceCode Apache-2.0; training data CC BY-NC 4.0Apache-2.0
Model size580M parameters8.7B parameters, built on Qwen3-8B and SigLIP2-400M
How you run itSelf-hosted with Hugging Face Transformers. README lists CUDA 11.8 and PyTorch 2.0.1. CPU users are pointed to a llama.cpp port.Self-hosted with llama.cpp, vLLM or Transformers. Int4, GGUF and AWQ builds exist. Ollama and SGLang support were still pending on the model card.
Output formatsPlain text, Markdown, LaTeX, TikZ, SMILES, kernPlain text, Markdown, JSON
Region and coordinatesRegion OCR guided by box coordinates or colorNo bounding box or layout output
BenchmarksNot published in the READMEOpenBMB claims leading OCRBench and OmniDocBench PDF parsing results, but scores are given only as images
Known failure modesLoops characters midway through recognition (issue #226). Returns wrong text on images with no text (issue #235). Format mode is much worse than plain OCR mode (issue #317).No int4 VRAM figure published. No hosted SLA.

Sources

What each one is

GOT-OCR 2.0

Unified OCR model that reads plain text, tables, formulas, sheet music and charts.

GOT-OCR 2.0 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 10 files at onceNo file?

Use one, fall back to the other

{"model": "stepfun/got-ocr-2","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GOT-OCR 2.0 alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026