Hunyuan OCR vs Chunkr
Pick Hunyuan OCR if you want a ~1B self-hosted model for photo and scene text, image translation, or rare and historical scripts, and you are outside the EU, UK and South Korea. Pick Chunkr if you need a parsing pipeline that takes PDF, PPT, Word and images and returns layout-aware, chunked output for RAG, with a hosted API or a self-host option. The main split is model versus service: Hunyuan OCR is one OCR model, Chunkr is a layout and chunking pipeline around OCR.
Hunyuan OCRtencent/hunyuan-ocr | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 1.5 s / page | 3.0 s / page |
| Best for | Chinese documents and photos | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 100+ languages | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
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 need text spotting on photos and scene images, or text-image translation, from one ~1B model.
- You work with low-resource or ancient scripts, since it exposes 12 task types including those.
- You want to run on a laptop or consumer GPU through the llama.cpp GGUF path, with no per-page fees.
Choose Chunkr if
- You are chunking PDFs and slides for RAG and want layout analysis with bounding boxes in the same step.
- You want the choice of a hosted API or a Docker self-host with GPU, CPU-only and Mac ARM options.
- You need to ingest PDF, PPT, Word and image files, and you can point it at any OpenAI-compatible LLM endpoint.
Key differences
| Hunyuan OCR | Chunkr | |
|---|---|---|
| What it is | Lightweight end-to-end OCR VLM (~1B) for parsing, text spotting, extraction and image translation | Document parsing service with layout analysis, OCR with bounding boxes and semantic chunking |
| Licence | Tencent Hunyuan Community License; excludes EU, UK and South Korea; separate license above 100M monthly active users | AGPL-3.0 or a commercial license; closed-source use needs the commercial license |
| How you run it | Self-host only, via vLLM, Transformers or llama.cpp | Cloud API or self-host with Docker; self-host still needs an external LLM endpoint |
| Price | Free, you pay for compute | Hosted credit-based plans (prices not published here); open-source version free, you pay for compute and an LLM endpoint |
| Output formats | Markdown, HTML, LaTeX, JSON, plain text, bounding boxes | HTML, Markdown, JSON, bounding boxes |
| Benchmark | ParseBench-2 overall 67.11; ParseBench mean 63.86 (v1.5) | Not published |
| Known limits | Unified setup needs CUDA 13 and vLLM 0.25.1+; an archived 1.0 note said Transformers and vLLM outputs differed in accuracy | Open-source version uses community models that are less accurate than the cloud's; Excel is not supported in the open-source version |
Sources
What each one is
Hunyuan OCR
Small end-to-end OCR model from Tencent covering parsing, extraction and photo translation.
Hunyuan OCR detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "tencent/hunyuan-ocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Hunyuan OCR alternativesChunkr alternativesBest OCR models in 2026