OCRRouter

Unlimited OCR vs Hunyuan OCR

Pick Unlimited OCR for long reports and books that you want parsed in one request, under an MIT licence. Pick Hunyuan OCR for photos, scene text, image translation and small machines, since it is about 1B parameters and runs on a laptop through llama.cpp. The main split is document length and licence versus task range and hardware.

Unlimited OCRbaidu/unlimited-ocrHunyuan OCRtencent/hunyuan-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.2 s / page1.5 s / page
Best forBooks and very long documentsChinese documents and photos
InputsPDF, imagesPDF, images
Languages30+ languages100+ languages
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
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 a long report or book goes in as one request.
  • Unlimited OCR 2 scores 77.1 on MarathonDocBench versus 33.7 for the next model, as reported by Baidu.
  • The MIT licence allows commercial use with no copyleft, and there are no regional exclusions.

Choose Hunyuan OCR if

  • One model of about 1B parameters covers document parsing, text spotting, information extraction and image translation.
  • It runs on a laptop, consumer GPU or CPU through the llama.cpp GGUF path, while Unlimited OCR needs an NVIDIA GPU.
  • It outputs Markdown, HTML, LaTeX and JSON, and handles low-resource and ancient scripts.

Key differences

Unlimited OCRHunyuan OCR
LicenceMIT, commercial use allowedTencent Hunyuan Community License; excludes the EU, UK and South Korea; separate licence above 100M monthly active users
Size3B total, about 500M active per token (Unlimited OCR 2 is 3.34B)About 1B
How you run itSelf-host with vLLM, SGLang or transformers; hosted option in Baidu Cloud's OCR productSelf-host only, via vLLM, Transformers or llama.cpp
HardwareNVIDIA GPU with CUDA 12.9 or 13.0; version 2 under SGLang runs out of memory on 12 GB GPUs; no CPU-only useNVIDIA GPU with CUDA 13 recommended for the unified vLLM setup; llama.cpp GGUF for CPU, consumer GPU or laptop
Output formatsMarkdown, plain text, bounding boxesMarkdown, HTML, LaTeX, JSON, plain text, bounding boxes
Multi-page and context40+ pages in one pass; context capped at 32,768 tokens; multi-page input only in base modeImages up to 4K and a 128K context window in v1.5
Known failureText repetition and looping (issue #55), hallucinated text (issue #58), bbox coordinate loops on GB10 GPUs under SGLang (issue #114); bold and italic styling mostly lostArchived 1.0 note said Transformers and vLLM outputs differed in accuracy; ParseBench-2 overall 67.11 with text score 62.88 in public CI replay

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

Hunyuan OCR

Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.

Hunyuan OCR 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": ["tencent/hunyuan-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Unlimited OCR alternativesHunyuan OCR alternativesBest OCR models in 2026