Qianfan OCR vs Chunkr
Pick Qianfan OCR when you want a single open-weight model under Apache-2.0 that parses multilingual pages, handwriting, tables and formulas on your own GPU. Pick Chunkr when the job is RAG ingestion of PDFs, slides and Word files, where you want layout analysis, bounding boxes and semantic chunking behind one service. The main split is that Qianfan OCR is a 4B model with published benchmarks, while Chunkr is a parsing service with no published benchmark scores.
Qianfan OCRbaidu/qianfan-ocr | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | OCR API | OCR API |
| Price | 2 credits / page | 14 credits / page |
| Per 1,000 pages | $2.00 | $14.00 |
| Typical speed | 2.0 s / page | 3.0 s / page |
| Best for | Chinese documents | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | Chinese, English and more | Multilingual |
| Max pages per request | 200 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | No | ✓ 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 Qianfan OCR if
- It scores 93.12 on OmniDocBench v1.5, 79.8 on olmOCR-Bench and 880 on OCRBench, while Chunkr publishes no benchmark scores.
- The Apache-2.0 licence allows commercial use with no commercial licence to buy.
- It covers 192 languages, handwriting and scene text, and outputs Markdown, JSON, HTML, LaTeX and bounding boxes.
Choose Chunkr if
- It does semantic chunking on top of layout analysis and OCR with bounding boxes, which suits RAG pipelines over PDFs and slides.
- It accepts PDF, PPT, Word and images, and can run in the cloud or self-hosted via Docker with GPU, CPU-only and Mac ARM options.
- It works with any OpenAI-compatible LLM endpoint, so you choose the model behind it.
Key differences
| Qianfan OCR | Chunkr | |
|---|---|---|
| Licence | Apache-2.0 | AGPL-3.0 or commercial licence; closed-source use needs the commercial one |
| What it is | 4B end-to-end document parsing model (Qwen3-4B language model) | Parsing service with layout analysis, OCR and semantic chunking |
| How you run it | Self-host the open weights, or use the Baidu Qianfan platform | Hosted cloud API, or open-source self-host that still needs an external LLM endpoint |
| Price | Free self-hosted (you pay for compute); hosted via Baidu Qianfan platform | Hosted credit-based plans, official prices not verified; open-source version free (you pay for compute and an LLM endpoint) |
| Output formats | Markdown, JSON, HTML, LaTeX, bounding boxes | HTML, Markdown, JSON, bounding boxes |
| Benchmarks | OmniDocBench v1.5 93.12; olmOCR-Bench 79.8; OCRBench 880 (reported by the authors) | Not published |
| Known weak spots | 1.024 pages per second on an A100 even with W8A8; thinking mode can emit up to 16,384 tokens; not suited to CPU-only deployment | Open-source version uses community models, less accurate than the cloud's in-house models; no Excel support in the open-source version |
Sources
What each one is
Qianfan OCR
Baidu's OCR-tuned vision model. Strong on Chinese documents and tables.
Qianfan 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": "baidu/qianfan-ocr","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Qianfan OCR alternativesChunkr alternativesBest OCR models in 2026