JigsawStack Logo

Beta

vOCR API

OCR + AI = Magic

Extract data from any document type in a consistent structure with fine-tuned vLLMs for the highest accuracy

vOCR Preview (Alpha)

Try more configurations ->

Sign up for free to run vOCR preview

Trusted by builders at

AI Optical character recognition (OCR)

Mix the power of OCR AI with fine-tuned LLMs to extract and accurately correct text from images and documents

Structured data

Get structured data in JSON format categorized by line and word level, including pixel coordinates for each word to form bounding boxes

File & document types

File support including PDF, PNG, JPEG from passports, invoices, complex images and more

Blazing fast speed

Run millions of images in seconds with the latest AI models and GPUs globally distributed for low latency

Tagging

Get image AI tagging classification for your images to understand the content and context of the image

Secure and private

Keep your data secure and private with end-to-end encryption and containerized AI models for processing data

Integrate vOCR on any platform

JavaScript

Python

PHP

Ruby

Go

Java

Swift

Dart

Kotlin

C#

cURL

npm i jigsawstack

vOCR use cases

5 ways our customers use JigsawStack's vOCR to build applications

KYC automation

Automate your KYC process by securely extracting text from documents to verify customer identity

Fraud detection

Detect fraudulent activities by analyzing risk factors in documents and images using AI tagging classification

Accessibility

Increase accessibility seamlessly by accurately extracting text from images without the need for manual transcription

Build document solutions

Powered by AI, build document solutions that can extract text from documents and images for various layouts

Healthcare or legal

Safely extract information from sensitive documents and images with end-to-end encryption for compliance and digital transformation

Features for every developer

Structured data

All models have been trained from the ground up to response in a consistent structure on every run

Automatic scale

Serverlessly run BILLIONS of models concurrently in less than 200ms and only pay for what you use

Purpose-Built Models

Purpose-built models trained for specific tasks, delivering state-of-the-art quality and performance

Easy integration

Fully typed SDKs, clear documentation, and copy-pastable code snippets for seamless integration into any codebase

Observability

Real-time logs and analytics. Debug errors, track users, location maps, sessions, countries, IPs and 30+ data points

Secure & Private

Secure and private instance for your data. Fine grained access control on API keys.

Global first models

Multilingual

Global support for over 160+ languages across all models

Global training datasets

We collect training data from all around the world to ensure our models are as accurate no matter the locality or niche context

Distributed GPUs

90+ global GPUs to ensure the fastest inference times all the time

Smart cache

Automatic smart caching to lower cost and improve latency

Community of AI Engineers shipping faster with us

The missing piece to your tech stack