GLM-OCR vs Unlimited OCR
Pick GLM-OCR for high-volume PDF to Markdown on a budget, academic papers with formulas, and form fields pulled into a JSON schema. Pick Unlimited OCR for long reports and books parsed in one pass, or when you need bounding boxes. The main split is scale and output: GLM-OCR is a 0.9B model with a $0.03 per million token API but a 100-page cap, while Unlimited OCR is a 3B model that handles 40+ pages in one forward pass and returns block types and boxes.
GLM-OCRzai/glm-ocr | Unlimited OCRbaidu/unlimited-ocr | |
|---|---|---|
| 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 | 1.2 s / page |
| Best for | Low-cost general documents | Books and very long documents |
| Inputs | PDF, images | PDF, images |
| Languages | 100+ languages | 30+ languages |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | No | No |
| Math | ✓ Yes | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | 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 GLM-OCR if
- It has a hosted Z.ai API at $0.03 per million tokens for input and output, so high-volume PDF to Markdown stays cheap.
- It scores 94.62 on OmniDocBench v1.5 per its model card, and it suits academic papers with formulas.
- It can extract fields into a user-defined JSON schema, which helps with forms.
Choose Unlimited OCR if
- It parses 40+ pages in a single forward pass with roughly constant memory, so long reports and books go in one request.
- It returns block types and bounding boxes alongside text, which suits layout-aware extraction.
- It scores 46.17 mean on ParseBench versus 29.6 for GLM-OCR, and Unlimited OCR 2 scores 77.1 on MarathonDocBench versus 33.7 for the next model, per Baidu.
Key differences
| GLM-OCR | Unlimited OCR | |
|---|---|---|
| Model size | 0.9B parameters | 3B total, about 500M active per token; Unlimited OCR 2 is 3.34B |
| Licence | MIT for the weights; the SDK repo and bundled PP-DocLayoutV3 are Apache-2.0 | MIT |
| How you run it | Z.ai API, or self-host with vLLM, SGLang, Ollama or transformers | Self-host with vLLM, SGLang or transformers; also hosted in Baidu Cloud's OCR product |
| Price | API: $0.03 per million tokens for input and output. Self-hosted: free, you pay for compute | Free self-hosted, you pay for compute. Hosted pricing: Not published |
| Output formats | Markdown, JSON, plain text | Markdown, plain text, bounding boxes |
| Limits | API caps input at 100 pages, 50 MB per PDF and 10 MB per image | Context capped at 32,768 tokens; multi-page input only works in base mode |
| Known failures | Repeated output (issue #220), dropped table footer rows (#240), lost comma decimals in cropped tables (#241), no aarch64 Linux (#227) | Repetition loops (issue #55), hallucinated text (#58), mostly lost text styling, SGLang bbox loops on GB10 GPUs (#114), version 2 runs out of memory on 12 GB GPUs (#116) |
Sources
- GLM-OCR Hugging Face model card
- Z.ai GLM-OCR docs and pricing
- GLM-OCR issue #240 missing table rows
- Unlimited OCR Hugging Face model card
- MarkTechPost on Unlimited OCR 2
- Unlimited OCR issue #116 OOM on 12 GB
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 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": "zai/glm-ocr","fallbacks": ["baidu/unlimited-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
GLM-OCR alternativesUnlimited OCR alternativesBest OCR models in 2026