Nanonets

Best for: Regulated or enterprise workloads - compliance attestations and an enterprise plan; AI agents and automation - an agent-ready surface (MCP / llms.txt); Teams needing broad API coverage out of the box

Avoid if: You want to try it free before paying

• █████▒░░░░
  55 / 100
  Agent friendliness
• ██████░░░░
  60 / 100
  Pricing transparency
• ██████░░░░
  60 / 100
  Setup speed
• ████▒░░░░░
  45 / 100
  Docs quality
• ███████▒░░
  75 / 100
  Procurement ease
• █████████░
  90 / 100
  Trust readiness

Scores are computed deterministically from this profile's published, sourced fields (pricing, compliance, capabilities, docs and developer-surface signals) - not from reviews or paid placement. Each axis is 0-100; an unknown signal scores 0 for that axis. Procurement ease is the inverse of buying friction (higher = easier to adopt).

Pricing model

Usage-based [2]nanonets.com/pricing“You pay per block run. Priced by complexity.”docs.nanonets.com/docs/base-price-per-unit“Data Extraction AI: 0.30 credits/run ... Classification, Detection AIs: 0.10 credits/run each ... Control Flows: Free”

Published pricing

✓ Yes [3]nanonets.com/pricing“Simple operations: $0.02 per run; Standard AI: $0.10 per run; Complex AI: $0.30 per run”docs.nanonets.com/docs/base-price-per-unit“Data Extraction AI: 0.30 credits/run (all plans) ... Import Methods — Base tier (Email, API, cloud storage): 0.04 credits/run”

Free tier

✗ No [4]nanonets.com/pricing“Start free. No credit card.”nanonets.com/pricing“Start free with $200 in credits and scale as your volume grows.”

Self-serve signup

✓ Yes [5]nanonets.com/pricing“Start automating immediately. No platform fees, no commitments. Pay only for what you use.”nanonets.com/pricing“Free accounts available at accounts.nanonets.com/signup with no credit card required”

Requires sales call

✗ No

Enterprise plan

✓ Yes [6]nanonets.com/pricing“For large processing volumes with compliance, security, and deployment requirements.”nanonets.com/pricing“HIPAA & SOC 2 compliance ... Private cloud / on-prem deployment options”

• Receipts / invoices
• Custom models
• LLM / RAG-ready output

Supported actions

parse (document to structured markdown), extract (schema-compliant typed objects with confidence scores and bounding boxes), split (classify and route document types), chunk (context-aware chunking for RAG), vqa (visual question answering over documents), image classification prediction, OCR sync prediction (file upload), OCR async prediction (file upload), OCR prediction via URL, model training, file upload to model, file review and assignment, file deletion and update, prediction retrieval by file ID or page ID, webhook export configuration, integration query execution, data export to accounting software, cloud storage, databases [7]nanonets.com/research/nanonets-ocr-s/“transforms documents into structured markdown with intelligent content recognition and semantic tagging ... understands document structure and content context (like tables, equations, images, plots, watermarks, checkboxes, etc.)”docs.nanonets.com/docs/nanonets-overview“Data extraction and formatting ... Workflow automation with conditional logic ... File approvals and reviews ... Data exports to accounting software and business tools”docs.nanonets.com/docs/webhook-export“Nanonets can notify you when your files have been processed. By setting up a Webhook, you can configure Nanonets to send notifications directly to a URL of your choice.”

Regions

United States, European Union, Asia-Pacific [8]security.nanonets.com/geography-specific-requirements.md“host their data exclusively in a region of their chosing like the US or EU etc. In such a setup no data leaves the geography”nanonets.com“Data residency options for US, EU, and APAC regions, with the note that "customer data never leaves your boundary."”

Languages

200+ languages for character/word recognition, 50 languages for handwriting recognition [9]docs.nanonets.com/docs/language-supported“Nanonets supports character/word recognition in over 200+ languages including but not limited to:”

Input types

PDF, PNG, JPG, TIFF, CSV, XLS, XLSX, TXT, DOCX [10]github.com/NanoNets/nanonets-go“Support for multiple formats including PDFs, images (JPG, PNG, TIFF), Excel files, and scanned documents”docs.nanonets.com/docs/nanonets-overview“The platform handles invoices, receipts, purchase orders, contracts, claims, forms, bank statements, driver's licenses, passports, and bills of lading.”

Output types

JSON, Markdown, HTML (tables), structured key-value extraction, bounding boxes with confidence scores [11]nanonets.com/research/nanonets-ocr-s/“The model delivers "intelligently formatted markdown output that's ready for downstream processing by Large Language Models"”docs.nanonets.com/docs/webhook-export“The JSON payload includes fields like `prediction`, `predicted_boxes`, `moderated_boxes`, and `raw_ocr` containing extracted data details.”

Webhooks

✓ Yes [12]docs.nanonets.com/docs/webhook-export“Webhooks allow you to receive real-time notifications at a specified URL when a file is processed and ready for export.”docs.nanonets.com/docs/webhook-export“five export triggers: "On Inference," "On All Validations Passing," "On Approval," "On Assignment," and "On Rejection."”

Sandbox / test mode

✗ No

SDK languages

Python, Node.js, Go [13]github.com/NanoNets/nanonets-python-client“A Python client for the NanoNets API ... enables developers to "build custom deep learning models for images."”github.com/NanoNets/nanonets-go“The NanoNets Go SDK is a client library for the Nanonets API, an AI-powered intelligent document processing platform.”github.com/NanoNets/ocr-js-sdk“A Node.js SDK for NanoNets' Optical Character Recognition service, enabling developers to integrate OCR capabilities into their applications.”

MCP server

✓ Yes [14]github.com/NanoNets/docstrange/tree/main/mcp_server_module“This is a Model Context Protocol (MCP) server enabling Claude Code to interact with PDF documents through the docstrange library, focused on document navigation and search capabilities”

SOC 2

SOC 2 Type II [15]legal.nanonets.com/security-policy“Nanonets is SOC 2 compliant and ISO/IEC 27001 certified, with independently attested SOC 2 Type I and Type II reports available upon request.”nanonets.com/pricing“HIPAA & SOC 2 compliance”

HIPAA

✓ Yes [16]nanonets.com/pricing“HIPAA & SOC 2 compliance”nanonets.com/enterprise“SOC II, GDPR & ISO 27001 Certified. Nanonets is certified for highest grade security certifications”

GDPR

✓ Yes [17]legal.nanonets.com/gdpr“Nanonets has appointed a Data Protection Officer. For inquiries, contact privacy@nanonets.com”nanonets.com/enterprise“SOC II, GDPR & ISO 27001 Certified. Nanonets is certified for highest grade security certifications”

ISO 27001

✓ Yes [18]legal.nanonets.com/security-policy“Nanonets is SOC 2 compliant and ISO/IEC 27001 certified, with independently attested SOC 2 Type I and Type II reports available upon request.”nanonets.com/enterprise“SOC II, GDPR & ISO 27001 Certified. Nanonets is certified for highest grade security certifications”

PCI DSS

✗ No

Published SLA

✓ Yes [19]legal.nanonets.com/service-level-agreement“Nanonets will use commercially reasonable efforts to make each Service available with an uptime of 99.5% of each calendar month”legal.nanonets.com/service-level-agreement“Scheduled Maintenance will not exceed eight (8) hours per month ... Nanonets notifies Customer at least twenty-four (24) hours in advance”

Rate limits

Instant Learning Models: 5 pages/minute baseline; Custom models: 20 pages/minute baseline. Rate limits apply per model in a 1-minute window on all POST requests in the OCR Predict section. [20]support.nanonets.com/hc/en-us/articles/26225175018513-Rate-Limiting“For Instant Learning Models, the baseline rate-limit is 5 pages/minute. For Custom models, the baseline rate-limit is 20 pages/minute.”docs.nanonets.com/reference/how-to-handle-429-error

Known restrictions

Rate limits apply per model: 5 pages/min (Instant Learning) and 20 pages/min (Custom), Default data storage in the USA (US, EU, APAC data residency available on Enterprise/private deployment), SOC 2 and ISO 27001 reports available only upon NDA request, On-premise and private cloud deployment available on Enterprise tier only, SAML SSO/SCIM available on Enterprise tier only, HIPAA BAA available on Enterprise tier only [21]legal.nanonets.com/security-policy“Nanonets is SOC 2 compliant and ISO/IEC 27001 certified, with independently attested SOC 2 Type I and Type II reports available upon request.”nanonets.com/pricing“HIPAA & SOC 2 compliance ... Private cloud / on-prem deployment options”security.nanonets.com/geography-specific-requirements.md“host their data exclusively in a region of their chosing like the US or EU etc. In such a setup no data leaves the geography”

• Docs
• API reference
• llms.txt
• Status page

Docs rendering: static · llms.txt present

API style

rest

Base URL

https://app.nanonets.com/api/v2

Version

v2

Versioning

url

Stability

ga

Auth methods

api_key, basic

Error format

vendor-specific

Rate limit

20 / minute

SDKs

• Python nanonets · repo
• Node.js @nanonets/optical-character-recognition · repo
• Go · repo

• Auth docs
• Quickstart
• MCP server
• Webhook events

Launched

2017-01-01

Notable customers

Roche, Mondelez, Asian Paints, Japan Tobacco International, VFS Global

• Amazon Textract

  "Automatically extract printed text, handwriting, layout elements, and data from any document"

  Usage · public pricing · self-serve

• Veryfi

  "Documents into Data - securely, in seconds"

  Hybrid · free tier · public pricing · self-serve

• Google Document AI

  "A document processing and understanding platform that takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume."

  Usage · public pricing · self-serve

• Azure AI Document Intelligence

  "Azure Document Intelligence in Foundry Tools is a machine-learning based OCR and intelligent document processing service to automate extraction of key data from forms and documents."

  Usage · free tier · public pricing · self-serve

• Extend

  "Turn documents into high quality data"

  Hybrid · public pricing · self-serve

• Mindee

  "Turn your document data into structured JSON with high-reliability. Zero model training required."

  Hybrid · public pricing · self-serve

Nanonets alternatives · Nanonets vs Amazon Textract · All OCR & Document Parsing APIs APIs

Each field above carries a numbered source - hover for a preview, click to jump here.

1. ↑Description: nanonets.com · docs.nanonets.com
2. ↑Pricing model: nanonets.com · docs.nanonets.com
3. ↑Published pricing: nanonets.com · docs.nanonets.com
4. ↑Free tier: nanonets.com · nanonets.com
5. ↑Self-serve signup: nanonets.com · nanonets.com
6. ↑Enterprise plan: nanonets.com · nanonets.com
7. ↑Supported actions: nanonets.com · docs.nanonets.com · docs.nanonets.com
8. ↑Regions: security.nanonets.com · nanonets.com
9. ↑Languages: docs.nanonets.com
10. ↑Input types: github.com · docs.nanonets.com
11. ↑Output types: nanonets.com · docs.nanonets.com
12. ↑Webhooks: docs.nanonets.com · docs.nanonets.com
13. ↑SDK languages: github.com · github.com · github.com
14. ↑MCP server: github.com
15. ↑SOC 2: legal.nanonets.com · nanonets.com
16. ↑HIPAA: nanonets.com · nanonets.com
17. ↑GDPR: legal.nanonets.com · nanonets.com
18. ↑ISO 27001: legal.nanonets.com · nanonets.com
19. ↑Published SLA: legal.nanonets.com · legal.nanonets.com
20. ↑Rate limits: support.nanonets.com · docs.nanonets.com
21. ↑Known restrictions: legal.nanonets.com · nanonets.com · security.nanonets.com

Every field change, who made it, and when - from our audited data pipeline and editors.

1. 2026-06-15 Score Agent Friendliness: 30 → 55
2. 2026-06-15 Score Docs Quality: 15 → 45
3. 2026-06-14 Robots Allows Agents: (none) → Yes
4. 2026-06-14 API Reference URL: (none) → https://docs.nanonets.com/reference
5. 2026-06-14 Llms Txt Present: No → Yes
6. 2026-06-14 Llms Txt URL: (none) → https://docs.nanonets.com/llms.txt
7. 2026-06-14 Has Structured Data: (none) → No
8. 2026-06-14 Capabilities: {} → {"custom_models":true,"agentic_output":true,"receipts_invoices":true}
9. 2026-06-14 Summary Md: (none) → Nanonets is a document AI platform offering OCR, structured data extraction, do…
10. 2026-06-14 Score Docs Quality: 0 → 15
11. 2026-06-14 Llms Txt Present: (none) → No
12. 2026-06-14 Status Page URL: (none) → https://status.nanonets.com
13. 2026-06-14 Docs URL: (none) → https://docs.nanonets.com
14. 2026-06-14 Rendering: (none) → static
15. 2026-06-14 Best For: (none) → Regulated or enterprise workloads - compliance attestations and an enterprise p…
16. 2026-06-14 Score Agent Friendliness: (none) → 30
17. 2026-06-14 Score Pricing Transparency: (none) → 60
18. 2026-06-14 Score Setup Speed: (none) → 60
19. 2026-06-14 Score Docs Quality: (none) → 0
20. 2026-06-14 Score Procurement Friction: (none) → 75
21. 2026-06-14 Score Trust Readiness: (none) → 90
22. 2026-06-14 Avoid If: (none) → You want to try it free before paying
23. 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
24. 2026-06-14 Last Verified At: 2026-06-13T00:00:00.000Z → 2026-06-14T00:00:00.000Z
25. 2026-06-14 SDK Packages: Python, Node.js, Go → Python, Node.js, Go
26. 2026-06-13 ISO 27001: set to Yes
27. 2026-06-13 PCI DSS: set to No
28. 2026-06-13 SLA Published: set to Yes
29. 2026-06-13 SLA URL: set to https://legal.nanonets.com/service-level-agreement
30. 2026-06-13 Data Retention Policy URL: set to https://security.nanonets.com/data-retention-policy
31. 2026-06-13 Documented Rate Limits: set to Instant Learning Models: 5 pages/minute baseline; Custom models: 20 pages/minut…
32. 2026-06-13 Rate Limit Requests: set to 20
33. 2026-06-13 Rate Limit Window: set to minute
34. 2026-06-13 Known Restrictions: set to Rate limits apply per model: 5 pages/min (Instant Learning) and 20 pages/min (C…
35. 2026-06-13 Auth Methods: set to api_key, basic
36. 2026-06-13 Auth Docs URL: set to https://docs.nanonets.com/reference/authentication
37. 2026-06-13 API Style: set to rest
38. 2026-06-13 Base URL: set to https://app.nanonets.com/api/v2
39. 2026-06-13 API Version: set to v2
40. 2026-06-13 Versioning Scheme: set to url
41. 2026-06-13 Stability: set to ga
42. 2026-06-13 MCP URL: set to https://github.com/NanoNets/docstrange/tree/main/mcp_server_module
43. 2026-06-13 Quickstart URL: set to https://docs.nanonets.com/docs/integrate-via-api
44. 2026-06-13 Error Format: set to vendor-specific
45. 2026-06-13 Webhook Events URL: set to https://docs.nanonets.com/docs/webhook-export
46. 2026-06-13 Requires Verification: set to No
47. 2026-06-13 Price Basis: set to block run
48. 2026-06-13 Free Tier Limit: set to $200 in credits (no credit card required, credits never expire)
49. 2026-06-13 Launched At: set to 2017-01-01
50. 2026-06-13 Notable Customers: set to Roche, Mondelez, Asian Paints, Japan Tobacco International, VFS Global

This profile is crowd-editable - agents and humans can leave a review or propose a correction with a simple API call. No auth; requests are rate-limited and every submission is reviewed before it goes live. For a field edit, use any key from the Agent JSON in place of FIELD, and include a citation.

curl -X POST https://apio.sh/api/feedback/nanonets \
  -H 'Content-Type: application/json' \
  -d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'

curl -X POST https://apio.sh/api/suggest/nanonets/FIELD \
  -H 'Content-Type: application/json' \
  -d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'

All the ways to contribute →