GLM-OCR vs MonkeyOCR
Pick GLM-OCR for high-volume PDF to Markdown through a cheap API, or when you need MIT-licensed weights you can ship in a product. Pick MonkeyOCR for self-hosted parsing of English and Simplified Chinese papers with tables and formulas, but only for research, because its v1 weights need a written license for commercial use. The licence is the main split.
GLM-OCRzai/glm-ocr | MonkeyOCRmonkeyocr/monkeyocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 6 credits / page | 2 credits / page |
| Per 1,000 pages | $6.00 | $2.00 |
| Typical speed | 1.3 s / page | 1.5 s / page |
| Best for | Low-cost general documents | Chinese and English PDFs |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages | Chinese, English |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | No | No |
| Multilingual | ✓ Yes | No |
| 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 GLM-OCR if
- The weights are MIT, so you can use them commercially and in SaaS without asking anyone.
- You can call the Z.ai API at $0.03 per million tokens for input and output, or self-host with vLLM, SGLang, Ollama or transformers.
- It can extract fields into a user-defined JSON schema, which suits forms, and it reports 94.62 on OmniDocBench v1.5.
Choose MonkeyOCR if
- It reports the best overall OmniDocBench edit distance among the models it compared, 0.138 English and 0.206 Chinese for pro-3B.
- It runs on an 8GB RTX 4060 with quantized weights, and pro-1.2B is about 36% faster than pro-3B for about 1.6% lower accuracy.
- Output includes Markdown, JSON with block coordinates, LaTeX, HTML and a layout PDF, which helps when you need to know where each block sits on the page.
Key differences
| GLM-OCR | MonkeyOCR | |
|---|---|---|
| Licence | MIT for weights; Apache-2.0 for the SDK repo | Code Apache-2.0; v1 weights research and non-commercial only, commercial use needs a written license |
| How you run it | Z.ai API or self-host (vLLM, SGLang, Ollama, transformers) | Self-host only (LMDeploy or Docker) |
| Price | API $0.03 per million tokens; self-hosted free plus compute | Free for research when self-hosted; commercial use needs a separate license |
| Model size | 0.9B | 3B and 1.2B |
| Output formats | Markdown, JSON, plain text | Markdown, JSON, LaTeX, HTML, bounding boxes |
| Benchmarks | OmniDocBench v1.5 overall 94.62 (authors); ParseBench mean 29.6 (independent) | OmniDocBench overall edit distance 0.138 EN / 0.206 ZH, table TEDS 81.5 / 87.5 (pro-3B, authors) |
| Known failures | Repeated output without a stop sequence; drops table footer rows; loses comma decimal separators; no aarch64 Linux; API limit of 100 pages, 50 MB per PDF, 10 MB per image | Photographed text, handwriting, Traditional Chinese and multilingual text not fully supported; pro-3B about 0.49 pages/s on a 3090; Docker on 20/30/40-series and V100 needs a patched image |
Sources
- Hugging Face model card
- Z.ai GLM-OCR docs and pricing
- GLM-OCR GitHub
- Issue #240 missing table rows
- MonkeyOCR GitHub README
What each one is
MonkeyOCR
Open-source document parser that splits work into structure, recognition and relation steps.
MonkeyOCR 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": "zai/glm-ocr","fallbacks": ["monkeyocr/monkeyocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
GLM-OCR vs NougatGLM-OCR vs SmolDoclingUnlimited OCR vs MonkeyOCRPaddleOCR-VL vs MonkeyOCRTrOCR vs MonkeyOCRKraken vs MonkeyOCROCRmyPDF vs MonkeyOCRGLM-OCR vs OpenOCR
GLM-OCR alternativesMonkeyOCR alternativesBest OCR models in 2026