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.
Solid contracts, transparent operations, and an easy start — typically complete on four or five facets with one clear soft spot.
API Evangelist profiles Nanonets the way a machine reads it — 106 machine-readable artifacts across 10 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Nanonets scores 66.7/100 (strong), with a separate agent-readiness read of 68/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Nanonets
Each block below is one kind of artifact we hold for Nanonets. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 10
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
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 ...
Nanonets File Assignment API
Assign files to reviewers.
Nanonets File Delete API
Delete a processed file.
Nanonets File Export API
Retry exports to configured downstream destinations.
Nanonets File Review API
Approve and unapprove files post-extraction.
Nanonets File Update API
Update or add extracted field values on a file.
Nanonets Image Classification Predict API
Predict on uploaded images or image URLs against a classification model.
Nanonets OCR Predict API
Predict on uploaded files or file URLs against a Nanonets OCR model.
Nanonets OCR Retrieve API
Retrieve prediction results for a file, page, or batch.
Nanonets OCR Train API
Upload training images and train or retrain an OCR model.
Scroll within the panel for all 10 ·
Postman Collections 4
A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.
Ready-to-run Postman collections for exercising this provider's APIs.
Nanonets File Management API
POSTMANNanonets OCR API
POSTMANOpen Collections 4
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
Nanonets External Integrations API
OPEN COLLECTIONNanonets File Management API
OPEN COLLECTIONNanonets Image Classification API
OPEN COLLECTIONNanonets OCR API
OPEN COLLECTIONArazzo Workflows 12
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
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.
ARAZZOScroll within the panel for all 12 ·
Pricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Rate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Nanonets Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Nanonets Finops
FINOPSFeatures 21
The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.
Notable capabilities this provider offers.
Nanonets OCR-3 model
Highest-accuracy OCR model on the public IDP Leaderboard, ahead of GPT-5, Gemini, and Claude.
Instant Learning (zero-shot) models
Train an extraction model from a handful of examples or even from a written field description, without large labeled datasets.
Pre-built document models
Ready-to-use models for invoices, receipts, purchase orders, bills of lading, bank statements, passports, and driver's licenses.
Custom-trained OCR models
Upload images, annotate labels and tables, train and retrain a model tied to a unique `model_id`.
Document Classification and Routing
Classify incoming documents and route each to the correct extraction model and workflow.
Table extraction
Multi-page table parsing with per-cell bounding boxes, row/column indices, and OCR text.
Sync and async file processing
Sync endpoints optimized for ≤3-page files; async endpoints for larger documents with polling by `request_file_id`.
Workflow builder
No-code visual pipeline of imports, transformations, lookups, approvals, conditional routing, and exports.
Approval rules and review queues
Field- and cell-level approval rules with reviewer assignment, comments, validation status, and duplicate detection.
Python post-processing blocks
Custom Python blocks inside the workflow for bespoke data transformation and validation logic.
Generative AI blocks
LLM-powered transformation steps for normalization, enrichment, and classification.
PII Masking
Mask personally identifiable information before downstream export.
Confidence scoring
Per-field and per-cell confidence scores feed routing rules and human-in-the-loop review.
On-prem and private cloud deployment
Run the Nanonets OCR stack inside customer infrastructure with the OCR Docker offering.
White-label review and approval UI
Embed the Nanonets review experience under a customer-branded domain.
SAML SSO and SCIM
Enterprise-grade identity and lifecycle management.
Audit logs and SIEM integration
Enterprise audit trail with SIEM-ready export.
Data residency
US, EU, and APAC region choices for enterprise customers.
Open-source extraction toolkit (docext)
On-prem, OCR-free unstructured data extraction and benchmarking toolkit, MIT-licensed.
Document conversion (docstrange)
Convert any document, PDF, image, Word doc, PPT, or URL into Markdown, JSON, CSV, or HTML.
Agentic RAG (nanoindex)
Tree- and graph-based reasoning harness for long-document retrieval with citations down to the pixel.
Scroll within the panel for all 21 ·
Semantic Vocabularies 1
JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.
JSON-LD contexts and semantic vocabularies used across these APIs.
Nanonets Context
JSON-LDSpectral Rules 2
Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.
Nanonets API Rules
SPECTRALNanonets API Rules
SPECTRALJSON Schema 1
Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.
Standalone JSON Schema definitions for this provider's data models.
Nanonets Prediction
JSON SCHEMAExamples 2
Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.
Example request and response payloads for these APIs.
Security Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Use Cases 8
What developers actually build with this provider — captured so the catalogue answers 'what is this for', not just 'what does this expose'.
What developers build with this provider.
Accounts Payable automation
Multi-format invoice capture, 3-way matching, approval routing, and ERP posting (claimed 80% cost reduction).
Order management
Extract and reconcile purchase orders across formats and channels.
Logistics and shipping
Bill of lading, packing list, and customs document extraction.
Healthcare revenue cycle
Medical claim, EOB, and patient intake document processing under HIPAA BAA.
Contract analysis
Extract obligations, parties, dates, and renewal terms from contracts.
Claims handling
Insurance claim intake, FNOL document parsing, and adjudication support.
Vendor onboarding
Extract W-9, tax certificate, and KYB document data for vendor master records.
ID and insurance verification
Driver's license, passport, and insurance card capture for identity workflows.
Scroll within the panel for all 8 ·
Integrations 32
Pre-built integrations with other platforms tell you where this provider already fits in a stack.
Pre-built integrations with other platforms and tools.
SAP
ERP export connector for posting extracted data.
QuickBooks
Accounting export connector for invoices and bills.
Xero
Accounting export connector and lookup data source.
Sage
ERP export connector.
NetSuite
ERP export connector with credential setup guide and lookup support.
Zoho Books
Accounting export connector.
Salesforce
CRM export connector for routing extracted records into Salesforce objects.
HubSpot
CRM destination for extracted data.
Gmail
Email import and inbox-based intake.
Microsoft Outlook / Email
Email import action with run history.
Slack
Notification and collaboration channel.
Microsoft Teams
Notification and collaboration channel.
Jira
Project management destination.
Asana
Project management destination.
Google Drive
Import and export connector for cloud-stored documents.
Dropbox
Import and export connector.
Box
Cloud storage source.
OneDrive
Import and export connector.
SharePoint
Import and export connector.
Google Sheets
Lookup data source and export destination.
Google Docs
Export destination.
Microsoft Excel
Export destination.
Smartsheet
Export destination.
FTP server
Export destination for partner integrations.
Snowflake
Data warehouse destination.
Stripe
Payment and billing data source.
Zendesk
Support workflow integration.
Notion
Document destination.
Zapier
Trigger-based intake for arbitrary SaaS connections.
n8n
Open-source workflow automation via `n8n-nodes-nanonets`.
Webhooks
Push extracted data to any HTTP endpoint with a documented payload structure.
PostgreSQL / MySQL / MSSQL / MongoDB
External database integrations for lookups and execute-query operations.
Scroll within the panel for all 32 ·
Solutions 3
Packaged solutions the provider offers on top of the raw API surface.
Packaged solutions this provider offers.
Starter
Free tier with $200 in credits, API access, email import, cloud storage connectors, up to 3 users, and community support.
Growth
Volume-discount tier adding classification AI, barcode and signature detection, generative AI blocks, custom Python blocks, ERP and database integrations, AI reporting, and team...
Enterprise
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), ded...
Resources
Every other property we hold for Nanonets — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 4
Portal, sign-up, and the first successful call
Documentation 9
Reference material describing how the API behaves
Scroll within the panel for all 9 ·
Agent Surfaces 1
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 16
Pagination, idempotency, versioning, errors, and events
Scroll within the panel for all 16 ·
Build 16
SDKs, sample code, and the tooling you integrate with
Scroll within the panel for all 16 ·
Access & Security 3
Authentication, authorization, and security posture
Operate 2
Status, limits, changes, and where to get help
Commercial 4
Pricing, plans, and the legal terms of use
Company 1
The organization behind the API
← All providers · Data indexed from github.com/api-evangelist/nanonets · machine-readable index on apis.io