OCRRouter

DeepSeek-VL2 vs Chunkr

Pick DeepSeek-VL2 if you want to self-host an open-weights model for question answering on single-page documents and charts. Pick Chunkr if you need to turn PDFs, slides, Word files and images into HTML, Markdown or JSON with bounding boxes for RAG, through a cloud API or a self-hosted stack. The main split is that DeepSeek-VL2 is a vision language model, while Chunkr is a document parsing service with layout analysis and chunking.

DeepSeek-VL2deepseek/deepseek-vl2Chunkrchunkr/chunkr
TypeVision modelOCR API
Price2 credits / page14 credits / page
Per 1,000 pages$2.00$14.00
Typical speed3.0 s / page3.0 s / page
Best forCharts and tablesLayout-aware chunks for RAG
InputsimagesPDF, images, DOCX
LanguagesMainly English and ChineseMultilingual
Max pages per request5001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ 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 DeepSeek-VL2 if

  • Its full model scores 93.3 on DocVQA test, so it suits question answering over single-page documents.
  • The weights allow commercial use under the DeepSeek Model License, and the code is MIT.
  • Only 1.0B to 4.5B parameters are active per token, and Tiny runs under 40GB of GPU memory.

Choose Chunkr if

  • It returns HTML, Markdown, JSON and OCR with bounding boxes, and it chunks output for RAG.
  • It accepts PDF, PPT, Word and images, so you do not need to convert slides or Word files first.
  • You can use the hosted API or self-host with Docker (GPU, CPU-only and Mac ARM options) against any OpenAI-compatible LLM endpoint.

Key differences

DeepSeek-VL2Chunkr
What it isMixture-of-experts vision language model in Tiny, Small and full sizesDocument parsing service with layout analysis, OCR and semantic chunking
How you run itSelf-host the open weights onlyCloud API or open-source self-host; self-host needs an external LLM endpoint
LicenceMIT (code); DeepSeek Model License (weights, commercial use allowed)AGPL-3.0 or commercial license; closed-source products need the commercial license
PriceFree, you pay for computeHosted credit-based plans, official prices not verified; open-source version is free, you pay for compute and an LLM endpoint
Output formatsPlain text, MarkdownHTML, Markdown, JSON, bounding boxes
BenchmarksDocVQA test 93.3, ChartQA test 86.0, OCRBench 834 (Small), all from the authors' paperNot published
Known limitsOnly a few images per session, dynamic tiling turns off above two images, struggles with blurry images, Small needs about 80GB GPU memory without chunked prefillOpen-source version uses community models that are less accurate than the cloud's in-house models, and it does not support Excel

Sources

What each one is

DeepSeek-VL2

DeepSeek's mixture-of-experts vision models (December 2024) with OCR and table and chart understanding.

DeepSeek-VL2 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": "deepseek/deepseek-vl2","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

DeepSeek-VL2 alternativesChunkr alternativesBest OCR models in 2026