OCRRouter

Hunyuan OCR vs OCR.space

Pick OCR.space if you want a hosted API with a free tier of 25,000 requests per month and no GPU to manage, for example to make scanned PDFs searchable or to prototype. Pick Hunyuan OCR if you can self-host a ~1B model and need scene text spotting, image translation or low-resource scripts. The main split is deployment: Hunyuan OCR is free software you run on your own compute, OCR.space is a proprietary API with file size and page limits.

Hunyuan OCRtencent/hunyuan-ocrOCR.spaceocrspace/ocr-space
TypeOpen sourceOCR API
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed1.5 s / page1.5 s / page
Best forChinese documents and photosCheap simple OCR
InputsPDF, imagesPDF, images
Languages100+ languages20+ languages
Max pages per request500100
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
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 Hunyuan OCR if

  • You want to self-host a ~1B model, including on a laptop through the llama.cpp GGUF path, and pay only for compute.
  • You need photo and scene text spotting, text-image translation, or OCR for low-resource and ancient scripts in one model.
  • You need images up to 4K and a 128K context window (v1.5), with output as Markdown, HTML, LaTeX, JSON or bounding boxes.

Choose OCR.space if

  • You want a hosted API with no GPU or CUDA setup, and a free tier of 25,000 requests per month for prototypes or hobby projects.
  • You need to turn scanned PDFs into searchable PDFs, with per-word overlay coordinates returned.
  • You need Engine 3 for 200+ languages, tables, handwriting and checkboxes, and a paid plan with a 100% uptime or money back SLA.

Key differences

Hunyuan OCROCR.space
How you run itSelf-hosted via vLLM, Transformers or llama.cppHosted API; an on-premise version is sold separately
LicenceTencent Hunyuan Community License. It excludes the EU, UK and South Korea, and above 100M monthly active users you need a separate license.Proprietary
PriceFree software; you pay for computeFree: 25,000 requests/month. PRO $30/month for 300,000 requests. PRO PDF $60/month. Enterprise from $999/month.
Hardware and setupNVIDIA GPU with CUDA 13 and vLLM 0.25.1+ for the unified environment; GGUF path for CPU, consumer GPU or laptopNone on your side
File limitsImages up to 4K, 128K context window in v1.5Free: 1 MB files and 3 PDF pages. PRO: 5 MB. PRO PDF: 100 MB+ and 999+ pages.
Output formatsMarkdown, HTML, LaTeX, JSON, plain text, bounding boxesJSON, plain text, bounding boxes, searchable PDF, Markdown
Known weaknessesParseBench-2 overall 67.11 (text score 62.88). Archived 1.0 note said Transformers and vLLM outputs differed in accuracy.Free searchable PDFs carry a watermark. Engine 3 is slower on large files with less precise coordinates. Engine 2 lacks Greek.

Sources

What each one is

Hunyuan OCR

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

Hunyuan OCR details

OCR.space

Low-cost OCR API with a large free tier. Returns text, word boxes and searchable PDFs.

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

Questions

More comparisons

Hunyuan OCR alternativesOCR.space alternativesBest OCR models in 2026