OCRRouter

Pixtral vs Chunkr

Pick Chunkr if you need to parse PDFs, slides and Word files into HTML, Markdown or JSON with bounding boxes for a RAG pipeline. Pick Pixtral only if you already run on the Mistral API and want question answering over charts and documents. Pixtral 12B is deprecated and no longer maintained, so it is a poor base for a new OCR project.

Pixtralmistral/pixtralChunkrchunkr/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 forQuestions about document imagesLayout-aware chunks for RAG
InputsimagesPDF, images, DOCX
LanguagesMultilingualMultilingual
Max pages per request5001,000
TablesNo✓ Yes
HandwritingNoNo
MathNo✓ Yes
Bounding boxesNo✓ Yes
ConfidenceNoNo
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 Pixtral if

  • You already have an integration on the Mistral API and want to keep it.
  • You need question answering over charts and documents, where Mistral reports 90.7 ANLS on DocVQA and 81.8 on ChartQA.
  • You want Apache-2.0 open weights with no licence friction for closed products.

Choose Chunkr if

  • You need layout analysis, OCR with bounding boxes and semantic chunking for RAG over PDFs and slides.
  • You want structured output in HTML, Markdown or JSON from PDF, PPT, Word and image inputs.
  • You want to self-host with Docker on GPU, CPU-only or Mac ARM, using any OpenAI-compatible LLM endpoint.

Key differences

PixtralChunkr
What it isGeneral vision language model from Mistral AI: 12B Mistral Nemo decoder plus a 400M vision encoderDocument parsing service from Lumina AI: layout analysis, OCR with bounding boxes, semantic chunking
LicenceApache-2.0AGPL-3.0 or commercial licence; closed-source products need the commercial licence
How you run itMistral API (pixtral-12b-2409) or open weights you host yourselfCloud API or self-hosted open-source version; self-host still needs an external LLM endpoint
Price$0.15 per million input and output tokens at launch; free to self-host, you pay for computeCredit-based hosted plans, prices not published; open-source version is free, you pay for compute and an LLM endpoint
Output formatsPlain text, Markdown, JSONHTML, Markdown, JSON, bounding boxes
BenchmarksDocVQA 90.7 ANLS, ChartQA 81.8, MMMU 52.5 (reported by Mistral)Not published
Known failureReported to miss on handwriting, small fonts and non-Latin scripts; Q4 quantization degrades small text; deprecatedOpen-source version uses community models that are less accurate than the cloud's; no Excel support in the open-source version

Sources

What each one is

Pixtral

Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.

Pixtral 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": "mistral/pixtral","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Pixtral alternativesChunkr alternativesBest OCR models in 2026