OCRRouter

GLM-OCR vs Nougat

Pick GLM-OCR for commercial, high-volume PDF to Markdown work, including papers with formulas and schema-based field extraction. Pick Nougat only for non-commercial work on English arXiv-style papers where you want LaTeX output. The main reason is licence: Nougat's weights are CC-BY-NC, while GLM-OCR's weights are MIT.

GLM-OCRzai/glm-ocrNougatmeta/nougat
TypeOpen sourceOpen source
Price6 credits / page2 credits / page
Per 1,000 pages$6.00$2.00
Typical speed1.3 s / page3.0 s / page
Best forLow-cost general documentsarXiv-style papers
InputsPDF, imagesPDF, images
Languages100+ languagesMainly English
Max pages per request500200
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ YesNo
Confidence✓ YesNo
FormsNoNo
Multilingual✓ YesNo
On OCRRouterAvailableAvailable

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 model weights are MIT, so you can use it in a commercial product.
  • You can call the Z.ai API at $0.03 per million tokens for input and output, or self-host it with vLLM, SGLang, Ollama or transformers.
  • It can extract fields into a user-defined JSON schema, not just transcribe text.

Choose Nougat if

  • It was trained on arXiv and PubMed Central papers, so it fits English scientific papers.
  • It outputs LaTeX for equations and tables in Mathpix-compatible .mmd Markdown, which suits math-heavy PDFs.
  • It ships small and base checkpoints with a simple CLI and API, and costs nothing for non-commercial use.

Key differences

GLM-OCRNougat
LicenceMIT for model weights; the SDK repo and bundled PP-DocLayoutV3 are Apache-2.0Code MIT; weights CC-BY-NC, so no commercial use
How you run itZ.ai API or self-hosted (vLLM, SGLang, Ollama, transformers)Self-hosted Python package only
PriceAPI: $0.03 per million tokens for input and output. Self-hosted: free, you pay for computeFree for non-commercial use, you pay for compute
Output formatsMarkdown, JSON, plain textMarkdown (.mmd) and LaTeX
BenchmarksOmniDocBench v1.5 overall 94.62 (authors); ParseBench mean 29.6 (independent)Not published
LanguagesNot publishedWorks best on English; Chinese, Russian and Japanese do not work
Known failureRepeated output unless a stop sequence is set; drops table footer and summary rows; loses comma decimal separators in cropped tablesRepetition loops on 1.5% of test pages, more on out-of-domain documents; repetition detection can drop pages as MISSING_PAGE

Sources

What each one is

GLM-OCR

Small open-source OCR model from Z.ai with layout regions. MIT licensed.

GLM-OCR details

Nougat

Meta's model that converts academic PDFs to Markdown with LaTeX math.

Nougat details

Try 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": ["meta/nougat"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GLM-OCR alternativesNougat alternativesBest OCR models in 2026