Unlimited OCR vs Qwen-VL
Pick Unlimited OCR to turn long reports, books and bulk PDFs into Markdown with bounding boxes for RAG. It parses 40+ pages in one pass under an MIT licence. Pick Qwen-VL when OCR is one task among several, such as VQA, photos or screenshots with text, or JSON output, and you want one general model.
Unlimited OCRbaidu/unlimited-ocr | Qwen-VLqwen/qwen-vl | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 2 credits / page |
| Per 1,000 pages | $2.00 | $2.00 |
| Typical speed | 1.2 s / page | 2.0 s / page |
| Best for | Books and very long documents | Flexible extraction with prompts |
| Inputs | PDF, images | PDF, images |
| Languages | 30+ languages | 30+ languages |
| Max pages per request | 1,000 | 200 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | ✓ Yes |
| 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 Unlimited OCR if
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in as one request.
- Unlimited OCR 2 scores 77.1 on MarathonDocBench versus 33.7 for the next model, per Baidu.
- It is MIT licensed and emits Markdown, plain text, block types and bounding boxes.
Choose Qwen-VL if
- It is a general vision-language model, so one deployment covers OCR, reasoning and VQA on photos and screenshots.
- It reads 32 languages and handles low light, blur and tilted text, per Qwen.
- It comes in sizes from 2B to 235B-A22B under Apache-2.0 and can output JSON and HTML as well as Markdown and boxes.
Key differences
| Unlimited OCR | Qwen-VL | |
|---|---|---|
| Main job | Multi-page document parser, 40+ pages in one pass | General vision-language model with OCR and document parsing |
| Licence | MIT | Apache-2.0 (Qwen3-VL repository) |
| Output formats | Markdown, plain text, bounding boxes | Plain text, HTML, bounding boxes, JSON, Markdown |
| Model size | 3B total, about 500M active per token (Unlimited OCR 2 is 3.34B) | 2B, 4B, 8B, 32B dense; 30B-A3B and 235B-A22B MoE |
| Hardware | NVIDIA GPU with CUDA 12.9 or 13.0; version 2 under SGLang runs out of memory on 12 GB GPUs | FP8 checkpoints need an H100-class GPU and CUDA 12+; the 235B example uses 8-way tensor parallel on vLLM |
| Benchmark | ParseBench mean 46.17 (independent); MarathonDocBench 77.1 for version 2 (authors) | olmOCR-bench 64.6 for Qwen 3 VL 8B (independent), below dedicated OCR models |
| Known failure | Repetition and looping on some pages, hallucinated text, bbox coordinate loops on SGLang with GB10 GPUs, and most text styling lost (formatting score 0.97 on ParseBench) | Repeating loops, worse with greedy decoding and on low-quality images; one transformers version caused loops on 10-37% of OCR outputs versus 2-3% baseline |
Sources
- Hugging Face model card
- MarkTechPost on Unlimited OCR 2
- Issue #116 OOM on 12 GB
- Qwen3-VL GitHub
- Issue #1611 infinite repetition
- Chandra README benchmark table
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 detailsQwen-VL
Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.
Qwen-VL detailsTry 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": ["qwen/qwen-vl"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Unlimited OCR vs Granite DoclingUnlimited OCR vs Hunyuan OCRMinerU vs Qwen-VLGLM-OCR vs Qwen-VLQwen-VL vs SmolDoclingReducto Parse vs Unlimited OCRUnlimited OCR vs GOT-OCR 2.0Unlimited OCR vs PaddleOCR (PP-OCR)
Unlimited OCR alternativesQwen-VL alternativesBest OCR models in 2026