GLM-OCR vs Unstructured
Pick GLM-OCR for high-volume PDF to Markdown, academic papers with formulas, and schema-based field extraction from forms, where its $0.03 per million token API and 94.62 OmniDocBench v1.5 score fit. Pick Unstructured for ingesting mixed file types (PDF, HTML, Word, PowerPoint, email, images) into a RAG pipeline. Do not rely on either for tables where every row and number must survive: GLM-OCR drops footer rows and comma decimals, and the open-source Unstructured library scores 0.426 on table cell content.
GLM-OCRzai/glm-ocr | Unstructuredunstructured/unstructured | |
|---|---|---|
| Type | Open source | OCR API |
| Price | 6 credits / page | 20 credits / page |
| Per 1,000 pages | $6.00 | $20.00 |
| Typical speed | 1.3 s / page | 3.0 s / page |
| Best for | Low-cost general documents | Mixed file types into 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 | No |
| 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
- Its API costs $0.03 per million tokens for input and output, and self-hosting is free apart from compute.
- It can extract fields into a user-defined JSON schema, which suits forms, and it handles academic papers with formulas.
- It scores 94.62 on OmniDocBench v1.5 and ran at 1.86 PDF pages per second on a single replica in the authors' test.
Choose Unstructured if
- It reads PDFs, HTML, Word, PowerPoint, emails and images in one library, so mixed file ingestion needs no extra tools.
- The hosted platform gives you 10,000 free pages, then $0.015 per page.
- Strategies Auto, Fast, High-Res and VLM let you trade speed for quality, and Fast suits born-digital PDFs.
Key differences
| GLM-OCR | Unstructured | |
|---|---|---|
| Licence | MIT for the model weights; the SDK repo and bundled PP-DocLayoutV3 are Apache-2.0 | Apache-2.0 for the open-source library; the hosted platform is proprietary |
| How you run it | Z.ai API, or self-host with vLLM, SGLang, Ollama or transformers (0.9B model); no aarch64 Linux support | Self-host the Python library or use the hosted API |
| Price | API: $0.03 per million tokens for input and output. Self-hosted: free, you pay for compute | Hosted: first 10,000 pages free, then $0.015 per page. Business is custom. Open-source library is free |
| Output formats | Markdown, JSON, plain text | JSON, HTML, plain text, bounding boxes |
| Input limits | API caps input at 100 pages, 50 MB per PDF and 10 MB per image | Not published |
| Benchmark | OmniDocBench v1.5 overall 94.62 (authors); ParseBench mean 29.6 (independent) | Table cell content 0.426 (open source) vs 0.866 (hosted), from the vendor's own benchmark |
| Known table failures | Drops table footer and summary rows (issue #240); loses comma decimal separators in cropped table regions (issue #241) | hi_res tables cut off at edges and drop first letters (issue #3262); table OCR ignores language settings (issue #1694) |
Sources
- Hugging Face model card
- Z.ai GLM-OCR docs and pricing
- Issue #240 missing table rows
- Unstructured pricing
- Unstructured GitHub README
- Unstructured issue #3262
What each one is
Unstructured
Document ETL for RAG. Partitions many file types into typed elements; open-source library too.
Unstructured 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": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
GLM-OCR alternativesUnstructured alternativesBest OCR models in 2026