OCRRouter

docTR vs MiniCPM-V 4.5

Pick docTR when you need word-level text with coordinates from invoices and receipts and plan to feed your own extraction or train your own models in Python. Pick MiniCPM-V 4.5 when you want a local model that returns Markdown or JSON and can answer questions about a document on a single GPU or edge device. The main split is output: docTR gives words and boxes, MiniCPM-V gives text without layout or coordinates.

docTRmindee/doctrMiniCPM-V 4.5openbmb/minicpm-v
TypeOpen sourceVision model
Price1 credit / page2 credits / page
Per 1,000 pages$1.00$2.00
Typical speed0.9 s / page2.5 s / page
Best forWord-level OCR with positionsOCR on edge devices
InputsPDF, imagesimages
LanguagesMainly Latin scripts30+ languages
Max pages per request500500
TablesNo✓ Yes
HandwritingNo✓ Yes
MathNoNo
Bounding boxes✓ YesNo
Confidence✓ YesNo
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 docTR if

  • You need nested page, block, line and word JSON with coordinates for each word.
  • You want to pick your own detection and recognition architectures, with straight or rotated boxes.
  • You train your own models in Python, or want a key information extraction predictor under Apache-2.0.

Choose MiniCPM-V 4.5 if

  • You want Markdown or JSON output from a document instead of words and lines.
  • You need quantized on-device or edge OCR, with int4, GGUF and AWQ builds on llama.cpp and vLLM.
  • You want local document Q&A on a single GPU.

Key differences

docTRMiniCPM-V 4.5
TypeTwo-stage text detection and recognition library from Mindee, run in Python on PyTorch8.7B open-weight vision language model from OpenBMB, built on Qwen3-8B and SigLIP2-400M
Licence and priceApache-2.0, free self-hosted, you pay for computeApache-2.0 weights and code, free self-hosted, you pay for compute
How you run itPython library, plus Docker images; GPU images need CUDA 12.2 or newer on the hostllama.cpp, vLLM, Ollama or Transformers; Ollama and SGLang support were still pending official releases on the model card
Output formatsJSON, plain text, bounding boxesPlain text, Markdown, JSON
Coordinates and layoutWord, line and block coordinates, straight or rotated boxesNo bounding box or layout output
Tables and MarkdownNo table, formula or Markdown output; words and lines onlyMarkdown output; claims state of the art PDF parsing among general MLLMs on OmniDocBench
BenchmarksNot publishedOpenBMB claims leading OCRBench results, but the model card gives scores only as images, so numbers are hard to verify

Sources

What each one is

docTR

Open-source OCR library from Mindee with separate text detection and recognition models.

docTR 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": "mindee/doctr","fallbacks": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

docTR alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026