Skip to content
SPECIFICTION
Get listed

Surya

github.com

From $400/mo Free plan macOSLinuxAPISelf-hosted
Visit github.com
Spec score 8.7 #6 of 40 in OCR software

What it is

Surya is a 650M-parameter OCR model for extracting text and analyzing document structure. It handles layout, reading order and tables, and supports OCR in 91 languages. Surya 2 returns page content as structured blocks that can include HTML, polygons, bounding boxes, confidence values and reading order. Table recognition can provide row and column geometry; full mode can also return HTML with spanning cells and header rows. Equations found in page OCR are represented as KaTeX-compatible LaTeX within math tags. Users can work with a Python package, command-line tools or an interactive Streamlit app for images and PDFs. Layout, OCR and table recognition require an inference backend: vLLM on NVIDIA GPUs or llama.cpp on CPU and Apple Silicon, or a connection to an existing server. Surya is free and open source. The code uses Apache 2.0, while the model weights have a separate modified AI Pubs Open Rail-M license with commercial-use conditions. It is specialized for documents, not photos or natural scenes.

Spec sheet

Purpose
Surya is a 650M-parameter OCR model for text recognition, layout analysis, reading order, and table recognition.Read 9 Oct 2026 · github.com
Intended users
Datalab says its platform serves AI/ML teams, enterprises, and product teams building AI agents, RAG systems, and document automation workflows.Read 9 Oct 2026 · documentation.datalab.to
Support
Datalab lists community support on Free, email and Slack support on Team, and dedicated support on Enterprise.Read 9 Oct 2026 · datalab.to
License
The Surya code is Apache 2.0, while the model weights use a modified AI Pubs Open Rail-M license with commercial-use conditions described in the README.Read 9 Oct 2026 · github.com
Headquarters
Manhattan, New York, United StatesRead 28 Sep 2026 · github.com
Inference backends
Layout, OCR, and table recognition use vLLM on NVIDIA GPUs or llama.cpp on CPU and Apple Silicon, and can connect to an existing server.Read 9 Oct 2026 · github.com
Installation
The README installs Surya with pip install surya-ocr and lists Docker plus NVIDIA Container Toolkit for NVIDIA GPU use, or llama.cpp for CPU and Apple Silicon.Read 9 Oct 2026 · github.com
Interfaces
The project provides a Python package, command-line tools, and an interactive Streamlit app for images and PDFs.Read 9 Oct 2026 · github.com
Languages
The repository describes Surya as supporting OCR in 90+ languages.Read 9 Oct 2026 · github.com
Limitations
Surya is specialized for document OCR rather than photos or natural scenes, and layout, OCR, and table recognition require a running inference backend.Read 9 Oct 2026 · github.com
Managed access
Datalab offers a managed platform running Surya and Chandra, with $5 in free credits and a free public playground.Read 9 Oct 2026 · github.com
Math
Surya 2 recognizes equations inline in page OCR and returns them in KaTeX-compatible LaTeX inside math tags.Read 9 Oct 2026 · github.com
Output
Surya 2 returns page content as structured blocks with HTML, polygons, bounding boxes, confidence, and reading order.Read 9 Oct 2026 · github.com
Primary platform
desktopRead 23 Sep 2026 · github.com
Security and compliance
Datalab's pricing page lists a SOC 2 Type II report for every plan; BAA/DPA support is listed for Team and Enterprise.Read 9 Oct 2026 · datalab.to
Supported inputs
bothRead 23 Sep 2026 · github.com
Supported languages
91Read 23 Sep 2026 · github.com
Table recognition
Table recognition can return row and column geometry and, in full mode, HTML with spanning cells and header rows.Read 9 Oct 2026 · github.com

Plans and prices

Free Free $0 pay-as-you-go $20 monthly allowance on work email or $10 on personal email · 25 requests/min · 25 concurrency · community support Read 9 Oct 2026 · datalab.to
Team $400 a month $400 per month $400 monthly usage included, then pay-as-you-go · 400 requests/min · 400 concurrency · email + Slack support Read 9 Oct 2026 · datalab.to
Enterprise Priced on request Custom Custom usage, rate limits, and terms · dedicated support · VPC or fully air-gapped deployment Read 9 Oct 2026 · datalab.to

Every Surya plan and price →

Strong points and limits

Strong points

  • OCR support covers 91 languages.
  • Returns structured text, layout and reading order.
  • Table output can include cell geometry and HTML.
  • Offers Python, command-line and Streamlit interfaces.
  • Free and open source.

Limits

  • Not specialized for photos or natural scenes.
  • Layout, OCR and tables require an inference backend.
  • Model weights have separate commercial-use conditions.

Who it suits

Surya suits developers and teams building document OCR workflows who can provide a supported inference backend. It is a poor fit for photo or natural-scene recognition.

Verdict

Surya provides document-focused OCR with structured output, table recognition and equation handling. Check the inference requirements and the distinct code and model-weight licenses before adopting it.

Where Specifiction places it

Alternatives to SuryaAll alternatives →