invoice2data
invoice2data is a command-line tool and Python library for extracting structured information from PDF invoices for accounting workflows.
What invoice2data is
invoice2data is a command-line tool and Python library for extracting structured information from PDF invoices for accounting workflows. It reads invoice text using selectable backends such as pdfium, pdftotext, pdfminer, pdfplumber, and OCR tools, then matches the text against YAML or JSON templates. Those templates can define custom fields and multiple regular expressions for each field. The command-line tool can save results as CSV, JSON, or XML, and rename PDF files based on their contents. Optional plugins handle invoice line items and tables, including an opt-in Camelot plugin for advanced table parsing. Optional AI features can help draft templates from sample documents or extract fields when templates do not match. No AI runs unless a provider is configured; the default provider has no network access. Local OCR backends include docTR and PaddleOCR. invoice2data is free and open source under the MIT License, with pip and conda installation options. Its README defers canonical schemas for non-invoice documents such as waybills and purchase orders.
Good
- Free and open source under the MIT License
- Exports results as CSV, JSON, or XML
- Supports custom fields and multiple regexes per field
- Optional plugins can extract line items and tables
- Local OCR options keep data on the machine
Watch out
- Canonical schemas for non-invoice documents are deferred
- No paid support plan is described
- No SECURITY.md policy is set up
Who it suits
It suits accounting workflows that need structured data extracted from PDF invoices, including users who want to define their own templates or export results in common data formats. Users handling other document types should note that canonical schemas for those documents are deferred.
Verdict
invoice2data provides template-based invoice extraction with several text backends and export formats. Its optional AI and table tools extend the workflow, while non-invoice documents remain outside the stated canonical schema scope.
Plans and prices
From invoice2data's own pricing page, checked 4 Oct 2026.
| Plan | Price | What it gives you |
|---|---|---|
| invoice2data | Free | No paid tiers or usage limits stated on the pages reviewed |
The facts
Each one read from invoice2data's own pages, with the date it was checked.
What it does
- AI options
- Optional AI features can draft templates from sample documents or extract fields as a fallback when templates do not match.checked 4 Oct 2026
- AI providers
- The opt-in AI layer lists OpenAI, DeepSeek, Mistral, Gemini, and Ollama providers; Ollama can run locally without sending data off the machine.checked 4 Oct 2026
- Extraction
- It extracts PDF text through selectable backends including pdfium, pdftotext, pdfminer, pdfplumber, and OCR tools.checked 4 Oct 2026
- Installation
- The docs provide pip and conda installation, and state the default pdfium path needs no system libraries on Windows, macOS, or Linux.checked 4 Oct 2026
- Integration
- The project README lists an Odoo OCA module as a user of invoice2data.checked 4 Oct 2026
- Known scope limit
- The README says canonical schemas for non-invoice documents such as waybills, delivery notes, and purchase orders are deferred.checked 4 Oct 2026
- License
- The repository publishes invoice2data under the MIT License, which permits use, modification, distribution, sublicensing, and sale subject to its conditions.checked 4 Oct 2026
- OCR privacy
- The installation guide describes docTR and PaddleOCR as local OCR backends that keep data on the user's machine.checked 4 Oct 2026
- Outputs
- The command-line tool can write extracted results as CSV, JSON, or XML and can rename PDF files to match their contents.checked 4 Oct 2026
- Privacy behavior
- The default AI provider is a mock with no network access, and the docs say no AI runs unless a provider is configured.checked 4 Oct 2026
- Purpose
- invoice2data is a command-line tool and Python library that extracts structured information from PDF invoices for accounting workflows.checked 4 Oct 2026
- Security
- The repository's GitHub security page says no SECURITY.md policy is set up and no security advisories are published.checked 4 Oct 2026
- Support
- The repository invites issues and pull requests, and links to a contributor guide; it does not describe a paid support plan on the pages reviewed.checked 4 Oct 2026
- Table extraction
- Optional plugins support matching invoice line items and tables, including an opt-in Camelot plugin for advanced table parsing.checked 4 Oct 2026
- Templates
- It matches extracted text against YAML or JSON templates that can define custom fields and multiple regexes per field.checked 4 Oct 2026
The full review of invoice2data
Overview
invoice2data is a free, open-source command-line tool and Python library for turning PDF invoices into structured accounting data. It suits developers and teams comfortable configuring an extraction workflow; its flexibility is the draw, while its template-based approach makes it a poor fit for buyers seeking a ready-made invoice service.
Key features
Users can extract PDF text with selectable backends including pdfium, pdftotext, pdfminer and pdfplumber, or use OCR tools. YAML or JSON templates define the fields to capture and can apply multiple regular expressions to each field. This offers control over different invoice layouts, but requires users to create and maintain the rules that make extraction work.
The command-line tool exports results as CSV, JSON or XML and can rename PDFs according to their contents. Optional plugins handle invoice line items and tables, including an opt-in Camelot plugin for advanced table parsing. That makes the tool more useful when accounting workflows need structured line-level data, though the extra capabilities depend on selecting and configuring plugins.
Optional AI features can draft templates from sample invoices or extract fields when templates do not match. Providers include OpenAI, DeepSeek, Mistral, Gemini and Ollama. No AI runs until a provider is configured; the default is a mock with no network access. Ollama can run locally, as can the docTR and PaddleOCR OCR backends described in the installation guide. These local options matter for sensitive documents, while configuring a third-party AI provider means choosing a workflow beyond the default.
Installation is available through pip or conda, and the default pdfium path needs no system libraries on Windows, macOS or Linux. The project is published under the MIT License, which permits use, modification, distribution, sublicensing and sale subject to its conditions. Its README names an Odoo OCA module as a user. The repository welcomes issues and pull requests, but does not describe a paid support plan; its GitHub security page says no SECURITY.md policy is set up and no advisories are published.
Pricing
invoice2data costs nothing, with no paid tiers or usage limits stated. The free, MIT-licensed software is the only plan, so there is no paid level to add service or capacity. This is attractive for teams able to manage their own setup, but buyers who want a packaged service should compare commercial alternatives.
Platforms
invoice2data supports Linux, macOS and Windows, and can be self-hosted. Its command-line and Python-library format favors users who can incorporate software into their own environment rather than those looking for a turnkey app.
Who it's for
It is a strong fit for developers and accounting teams that want to define invoice fields, choose text or OCR backends, and control how extracted data is exported. It is less suitable for workflows centered on non-invoice documents: canonical schemas for waybills, delivery notes and purchase orders are deferred. Teams that depend on an established security policy or paid support should weigh that gap before adopting it.
Pros and cons
- Pros: Free, open-source software with no stated usage limits, plus multiple extraction backends and CSV, JSON and XML exports.
- Pros: Optional table and line-item tools, configurable templates, and local OCR or Ollama options give technical users control over both extraction and data handling.
- Cons: Template-driven extraction puts the work of defining and maintaining invoice rules on the user.
- Cons: Non-invoice canonical schemas are deferred, and the repository has no SECURITY.md policy or published security advisories.
Alternatives
Veryfi Invoices OCR API is worth considering when a hosted API across Android, iOS and web is preferable to managing an open-source tool. Its Starter plan is $500 a month, billed at a $500/mo minimum commitment, with invoices at $0.16 each and a 15-page maximum per transaction.
Parseur may suit teams that want a web and API service with a free allowance of up to 20 pages per month, one user and 90-day document retention. Its free plan also includes unlimited mailboxes and extracted fields.
Invofox offers an alternative for users who need a REST API and pre-trained models across invoices, receipts, utility bills, tickets and payslips. Its free plan includes 500 pages and community support, with API, web and self-hosted platforms.
Nanonets Invoice OCR is another API and self-hosted option, with a free Starter entry that begins with $50 in credits and then charges $100/month for 100 credits.
DocuClipper Invoice Approval is a paid alternative for teams seeking an invoice approval product with API access; its Starter plan is $20 a month when billed annually and includes 60 pages/month and unlimited users.
Tungsten Power PDF is a paid PDF editor for Windows, macOS, web, Android and iOS users who need PDF creation, editing and conversion.
ABBYY FlexiCapture for Invoices is another invoice-focused option, available through a demo and contact with ABBYY.
Datamolino is a paid option for teams seeking bill and receipt processing with approvals; its Start plan costs £17 a month, excluding VAT, for 100 bills and receipts per month, one company and unlimited users.
Browse more options in Invoice Processing Software and Invoice OCR Software.
Verdict
Choose invoice2data if you want a free, self-hostable invoice extraction tool that lets your team control templates, backends and output formats. Its main advantage is that flexibility without a stated usage cap; look elsewhere if you need turnkey workflows for varied document types, a published security policy or paid support.
Getting started
- Install invoice2data with pip or conda.
- Use the default pdfium path on Windows, macOS, or Linux without system libraries.
- Provide invoice PDFs and match their contents with YAML or JSON templates.
- Choose an available text or OCR backend.
- Optionally configure an AI provider, or add plugins for line-item and table extraction.
- Run the command-line tool to export CSV, JSON, or XML, or rename PDFs.
Limits worth knowing
The README defers canonical schemas for non-invoice documents such as waybills, delivery notes, and purchase orders. No usage limits or paid tiers are stated on the pages reviewed.
Questions
How much does invoice2data cost?
It is free, with no paid tiers or usage limits stated on the pages reviewed.
What platforms does it support?
The listed platforms are Linux, macOS, self-hosted, and Windows. The default pdfium path needs no system libraries on Windows, macOS, or Linux.
Is invoice2data open source?
Yes. The repository publishes it under the MIT License, which permits use, modification, distribution, sublicensing, and sale subject to its conditions.
Does it use AI by default?
No. AI runs only when a provider is configured, and the default mock provider has no network access.
Can invoice2data extract line items?
Yes. Optional plugins support invoice line-item and table matching, including an opt-in Camelot plugin for advanced table parsing.
Which AI providers are listed?
The opt-in AI layer lists OpenAI, DeepSeek, Mistral, Gemini, and Ollama. Ollama can run locally without sending data off the machine.
Alternatives to invoice2data
- 1

Veryfi Invoices OCR API
Free planAndroidiOSWebAPI8.2From $500 a month - 2
Circulus
AndroidiOSWebAPI7.6From $39.99 a month - 3

Parseur
Free planWebAPI7.6From $49 a month - 4
ChronoScan AP Invoice Processing
Free planWebAPISelf-hostedWindows7.5From €49 a year - 5

Gemina Invoice OCR API
Free planWebAPI7.3From $25 a month - 6

Invofox
Free planWebAPISelf-hosted7.3From $500 a month
