OCRRouter

GLM-OCR vs Chunkr

Pick GLM-OCR for high-volume PDF to Markdown, academic papers with formulas and schema-based field extraction, where a $0.03 per million token API and an MIT licence keep cost and legal risk low. Pick Chunkr for RAG chunking of PDFs, slides and Word files, or when you want self-hosted layout parsing with bounding boxes. Avoid GLM-OCR for financial tables where every row and decimal must survive.

GLM-OCRzai/glm-ocrChunkrchunkr/chunkr
TypeOpen sourceOCR API
Price6 credits / page14 credits / page
Per 1,000 pages$6.00$14.00
Typical speed1.3 s / page3.0 s / page
Best forLow-cost general documentsLayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
Languages100+ languagesMultilingual
Max pages per request5001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
Multilingual✓ Yes✓ Yes
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 Z.ai API costs $0.03 per million tokens for input and output, and self-hosting is free apart from compute.
  • Its model card reports 94.62 on OmniDocBench v1.5, and the authors measured 1.86 PDF pages per second on a single replica.
  • It can extract fields into a user-defined JSON schema, which suits forms.

Choose Chunkr if

  • It accepts PDF, PPT, Word and images, and returns HTML, Markdown, JSON and OCR with bounding boxes.
  • It is built around layout analysis and semantic chunking, which fits RAG pipelines over PDFs and slides.
  • It self-hosts through Docker with GPU, CPU-only and Mac ARM options, and works with any OpenAI-compatible LLM endpoint.

Key differences

GLM-OCRChunkr
LicenceMIT for the model weights; the SDK repo and bundled PP-DocLayoutV3 are Apache-2.0AGPL-3.0, or a commercial licence; closed-source products need the commercial licence
How you run itZ.ai API, or self-host with vLLM, SGLang, Ollama or transformers; no aarch64 Linux supportCloud API, or self-host with Docker (GPU, CPU-only, Mac ARM); self-host needs an external LLM endpoint
PriceAPI: $0.03 per million tokens for input and output. Self-hosted: free plus computeHosted credit-based plans, official prices not verified. Open-source version is free plus compute and an LLM endpoint
Output formatsMarkdown, JSON, plain text, plus schema-based field extractionHTML, Markdown, JSON and bounding boxes
Input limits and formatsAPI caps input at 100 pages, 50 MB per PDF and 10 MB per imagePDF, PPT, Word and images; Excel is not supported in the open-source version
BenchmarksOmniDocBench v1.5: 94.62 (authors). olmOCR-Bench: 75.2 (authors). ParseBench mean: 29.6 (independent)Not published
Known failure modesRepeats output unless a stop sequence is set; drops table footer and summary rows; loses comma decimal separators in cropped tablesThe open-source version uses community models that are less accurate than the cloud's in-house models

Sources

What each one is

GLM-OCR

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

GLM-OCR details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr 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": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

GLM-OCR alternativesChunkr alternativesBest OCR models in 2026