OCRRouter

Surya vs Pixtral

Pick Surya when you need layout, reading order, tables and bounding boxes from a small model you run yourself, including on a laptop. Pixtral 12B is a general vision model that did well on DocVQA, so it only fits question answering over documents and charts on an existing Mistral API setup. Mistral marks it as deprecated, so Surya is the safer choice for new OCR work.

Suryadatalab/suryaPixtralmistral/pixtral
TypeOpen sourceVision model
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed1.5 s / page3.0 s / page
Best forLayout and line-level OCRQuestions about document images
InputsPDF, imagesimages
Languages90+ languagesMultilingual
Max pages per request500500
Tables✓ YesNo
HandwritingNoNo
MathNoNo
Bounding boxes✓ YesNo
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 Surya if

  • It returns layout labels, reading order, OCR, HTML tables and KaTeX math with per-block bounding boxes from one 689M model.
  • It runs on CPU and Apple Silicon through llama.cpp, with peak memory of about 4-6 GB on an M4 Max.
  • It scores 83.7% on olmOCR-bench (per its authors) and reached 4.52 pages/s at 192 DPI on one H100 with vLLM.

Choose Pixtral if

  • It scores 90.7 ANLS on DocVQA (per Mistral), which suits question answering over documents and charts.
  • Its 128K token context lets you send many images in one request.
  • The Mistral API charged $0.15 per million input and output tokens at launch, and the weights are Apache-2.0, so teams already on that API can keep their integration.

Key differences

SuryaPixtral
What it isOCR, layout, reading order and table toolkit, 689M parametersGeneral vision language model, 12.4B parameters (12B decoder plus 400M vision encoder)
LicenceCode Apache-2.0. Weights under a modified AI Pubs Open Rail-M: free for research, personal use and companies under $5M funding or revenueApache-2.0
How you run itSelf-host only. Needs a separate vLLM or llama.cpp server; NVIDIA GPU, CPU or Apple SiliconMistral API (pixtral-12b-2409) or self-hosted open weights
PriceFree to self-host, you pay for compute. Commercial licence needed above $5M revenue or funding$0.15 per million input and output tokens at API launch. Free to self-host, you pay for compute
Output formatsJSON, HTML, LaTeX, bounding boxes, plain textPlain text, Markdown, JSON
BenchmarksolmOCR-bench 83.7%; 74.9% pass rate across 91 languagesDocVQA 90.7 ANLS; ChartQA 81.8; MMMU 52.5
Known failureSurya 2.5 table output lacks row and column geometry. Multilingual tables score 58.1. Not for handwriting or photosReported drops on handwriting, small fonts and non-Latin scripts. Q4 quantization is reported to hurt small text. Deprecated by Mistral

Sources

What each one is

Surya

Open-source OCR toolkit with line detection, layout analysis, reading order and tables.

Surya details

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

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

Questions

More comparisons

Surya alternativesPixtral alternativesBest OCR models in 2026