Nanonets
Nanonets is a no-code document AI and OCR platform that combines a custom-model OCR API, pre-built document models (invoices, receipts, purchase orders, bills of lading, passports, driver's licenses, bank statements), image classification, and a visual workflow builder with imports, transformations, lookups, approvals, and ERP/CRM/database exports. The Nanonets OCR-3 model and the open-source docext toolkit power the IDP Leaderboard number-one ranking. Enterprise tier adds SAML SSO, SCIM, role-based access, on-prem and private-cloud deployment, HIPAA, SOC 2 Type II, and ISO 27001.
APIs
Nanonets OCR API
Synchronous and asynchronous OCR prediction and training endpoints over `app.nanonets.com/api/v2/OCR/Model/{model_id}`. Upload files by local path or public URL, retrieve predic...
Nanonets Image Classification API
Classify images by file upload or by publicly accessible URL against a Nanonets image classification model. Supports batch URL submission for efficient prediction. Base path `/a...
Nanonets File Management API
Approve, unapprove, assign, update, delete, and export files within a Nanonets model. Drives the review-and-approval workflow, PATCH-based field updates, team assignment to spec...
Nanonets External Integrations API
List external integrations connected to a Nanonets account (Postgres, MySQL, MSSQL, MongoDB, and other databases) and execute generic SQL queries against them in the context of ...
Collections
Arazzo Workflows
Nanonets Async OCR Predict and Poll
Submit a large document for async OCR, then poll until the file-level prediction is ready.
ARAZZONanonets Async URL Predict Poll and Approve
Async-predict a document by URL, poll until ready, then approve the file.
ARAZZONanonets Batch Review Pending Files
List a model's recent predictions, then approve the first unmoderated file.
ARAZZONanonets Classify Image and Branch
Classify an uploaded image and branch on whether a top label was predicted.
ARAZZONanonets Page-Level Correct and Approve
Pull a single page's prediction, correct its fields, then approve the file.
ARAZZONanonets Predict and Assign Reviewer
Predict on a file, fetch the file-level result, and assign it to a reviewer.
ARAZZONanonets Predict and Enrich with Database
Extract a document, then validate it against an external database integration.
ARAZZONanonets Predict Correct and Re-export
Predict on a file, correct its extracted fields, and retry the export.
ARAZZONanonets Resolve Integration and Query
List external integrations, pick the first one, and run a SQL-style query.
ARAZZONanonets Sync Predict and Review
Run a sync OCR prediction on a small file, then approve or hold it for review.
ARAZZONanonets Upload Training Images and Train
Upload annotated local training images to an OCR model, then kick off training.
ARAZZONanonets Upload Training URLs and Train
Add training images to an OCR model from public URLs, then start training.
ARAZZOPricing Plans
Rate Limits
FinOps
Nanonets Finops
FINOPSFeatures
Highest-accuracy OCR model on the public IDP Leaderboard, ahead of GPT-5, Gemini, and Claude.
Train an extraction model from a handful of examples or even from a written field description, without large labeled datasets.
Ready-to-use models for invoices, receipts, purchase orders, bills of lading, bank statements, passports, and driver's licenses.
Upload images, annotate labels and tables, train and retrain a model tied to a unique `model_id`.
Classify incoming documents and route each to the correct extraction model and workflow.
Multi-page table parsing with per-cell bounding boxes, row/column indices, and OCR text.
Sync endpoints optimized for ≤3-page files; async endpoints for larger documents with polling by `request_file_id`.
No-code visual pipeline of imports, transformations, lookups, approvals, conditional routing, and exports.
Field- and cell-level approval rules with reviewer assignment, comments, validation status, and duplicate detection.
Custom Python blocks inside the workflow for bespoke data transformation and validation logic.
LLM-powered transformation steps for normalization, enrichment, and classification.
Mask personally identifiable information before downstream export.
Per-field and per-cell confidence scores feed routing rules and human-in-the-loop review.
Run the Nanonets OCR stack inside customer infrastructure with the OCR Docker offering.
Embed the Nanonets review experience under a customer-branded domain.
Enterprise-grade identity and lifecycle management.
Enterprise audit trail with SIEM-ready export.
US, EU, and APAC region choices for enterprise customers.
On-prem, OCR-free unstructured data extraction and benchmarking toolkit, MIT-licensed.
Convert any document, PDF, image, Word doc, PPT, or URL into Markdown, JSON, CSV, or HTML.
Tree- and graph-based reasoning harness for long-document retrieval with citations down to the pixel.
Use Cases
Multi-format invoice capture, 3-way matching, approval routing, and ERP posting (claimed 80% cost reduction).
Extract and reconcile purchase orders across formats and channels.
Bill of lading, packing list, and customs document extraction.
Medical claim, EOB, and patient intake document processing under HIPAA BAA.
Extract obligations, parties, dates, and renewal terms from contracts.
Insurance claim intake, FNOL document parsing, and adjudication support.
Extract W-9, tax certificate, and KYB document data for vendor master records.
Driver's license, passport, and insurance card capture for identity workflows.
Integrations
ERP export connector for posting extracted data.
Accounting export connector for invoices and bills.
Accounting export connector and lookup data source.
ERP export connector.
ERP export connector with credential setup guide and lookup support.
Accounting export connector.
CRM export connector for routing extracted records into Salesforce objects.
CRM destination for extracted data.
Email import and inbox-based intake.
Email import action with run history.
Notification and collaboration channel.
Notification and collaboration channel.
Project management destination.
Project management destination.
Import and export connector for cloud-stored documents.
Import and export connector.
Cloud storage source.
Import and export connector.
Import and export connector.
Lookup data source and export destination.
Export destination.
Export destination.
Export destination.
Export destination for partner integrations.
Data warehouse destination.
Payment and billing data source.
Support workflow integration.
Document destination.
Trigger-based intake for arbitrary SaaS connections.
Open-source workflow automation via `n8n-nodes-nanonets`.
Push extracted data to any HTTP endpoint with a documented payload structure.
External database integrations for lookups and execute-query operations.
Solutions
Free tier with $200 in credits, API access, email import, cloud storage connectors, up to 3 users, and community support.
Volume-discount tier adding classification AI, barcode and signature detection, generative AI blocks, custom Python blocks, ERP and database integrations, AI reporting, and team-wide credit sharing.
Tailored pricing with SAML SSO, SCIM, RBAC, HIPAA and SOC 2 compliance, private cloud or on-prem deployment, data residency, enterprise connectors (Salesforce, SAP, Oracle), dedicated support and SLAs, audit logs, SIEM integration, and whitelabel UI.