LandingAI Agentic Document Extraction (ADE)
"Convert any document into accurate, structured data." [1]
LandingAI Agentic Document Extraction (ADE) is a REST API that converts PDFs, spreadsheets, and other documents into structured data, with capabilities covering field extraction, table parsing, document classification, intelligent chunking, and confidence scoring. It suits teams in finance, healthcare, and legal sectors processing invoices, records, and compliance documents at scale. Pricing starts at $1.00 per 100 credits with a 1,000-credit free trial (90-day expiry), self-serve signup, and an enterprise tier. The service is SOC 2 Type II certified, HIPAA and GDPR compliant on Team and Enterprise plans, hosted in US and EU AWS regions, and offers Python and Node.js SDKs.
Best for / Avoid if
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
Scores
- 45 / 100Agent friendliness
- 85 / 100Pricing transparency
- 55 / 100Setup speed
- 45 / 100Docs quality
- 85 / 100Procurement ease
- 55 / 100Trust readiness
Pricing & procurement
- Pricing model
- Hybrid (base + usage) [2]
- Published pricing
- ✓ Yes [3]
- Free tier
- ✗ No [4]
- Self-serve signup
- ✓ Yes [5]
- Requires sales call
- ✗ No [6]
- Enterprise plan
- ✓ Yes [7]
| Plan | Item | Per | Amount | Source |
|---|---|---|---|---|
| Explore | 1,000 trial credits at signup (one-time, expires 90 days) | account (one-time) | $0 | source |
| Explore | 100 credits (US) | 100 credits | $1 | source |
| Explore | 76 credits (EU) | 76 credits | $1 | source |
| Team | Monthly plan fee (US) — includes 27,500 credits | month | $250 | source |
| Team | Monthly plan fee (EU) — includes 27,500 credits | month | $325 | source |
| Team | 110 credits (US, included/prepaid rate) | 110 credits | $1 | source |
| Team | 84 credits (EU, included/prepaid rate) | 84 credits | $1 | source |
| Team | Overage / prepaid credit (US) | credit | $0.01 | source |
| Team | Overage / prepaid credit (EU) | credit | $0.013 | source |
| Enterprise | Custom pricing | - | source | |
| Parse API — document page (DPT-2 model) | 3 credits/page | - | source | |
| Parse API — spreadsheet sheet (DPT-2 model) | 1 credit/sheet | - | source | |
| Parse API — embedded image (DPT-2 model) | 3 credits/image | - | source | |
| Parse API — document page (DPT-2 mini model) | 1.5 credits/page | - | source | |
| Zero Data Retention add-on — document page | +1 credit/page | - | source | |
| Zero Data Retention add-on — spreadsheet sheet | +1 credit/sheet | - | source | |
| Zero Data Retention add-on — embedded image | +1 credit/image | - | source | |
| Zero Data Retention add-on — DPT-2 mini document page | +1 credit/page | - | source | |
| Extract API — input characters | 1 credit per 5,000 input characters | - | source | |
| Extract API — output characters | 1 credit per 1,000 output characters | - | source | |
| Build Extract Schema API — input characters | 1 credit per 5,000 input characters | - | source | |
| Build Extract Schema API — output characters | 1 credit per 1,000 output characters | - | source | |
| Classify API — document page | 0.5 credits/page | - | source | |
| Section API — input characters | 1 credit per 5,000 input characters | - | source | |
| Section API — output characters | 1 credit per 1,000 output characters | - | source | |
| Split API — input characters | 1 credit per 5,000 input characters | - | source |
Capabilities
- Supported actions
- parse_document, extract_fields, classify_document, split_document, build_extract_schema, parse_jobs_async, section_document, figure_summary, visual_grounding, intelligent_chunking, table_extraction, confidence_scoring [8]
- Regions
- US (AWS US East Ohio), EU (AWS eu-west-1 Ireland) [9]
- Languages
- English, Chinese (Simplified), Chinese (Traditional), Dutch, French, German, Italian, Japanese, Korean, Portuguese, Russian, Spanish, Arabic, Czech, Danish, Finnish, Greek, Hebrew, Hindi, Indonesian, Norwegian, Polish, Swedish, Thai, Turkish, Vietnamese, Amharic, Bengali, Gujarati, Malayalam, Tamil, Telugu, Urdu [10]
- Input types
- PDF, JPEG, JPG, PNG, APNG, BMP, DCX, DDS, DIB, GD, GIF, ICNS, JP2, PCX, PPM, PSD, TGA, TIF, TIFF, WEBP, DOC, DOCX, PPT, PPTX, ODT, CSV, XLSX [11]
- Output types
- JSON, Markdown [12]
- Webhooks
- ✗ No [13]
- Sandbox / test mode
- ✗ No [14]
- SDK languages
- Python, Node.js [15]
- MCP server
- ✗ No [16]
Trust & compliance
- SOC 2
- SOC 2 Type II [17]
- HIPAA
- ✓ Yes [18]
- GDPR
- ✓ Yes [19]
- ISO 27001
- ✗ No [20]
- PCI DSS
- ✗ No [21]
- Published SLA
- ✗ No [22]
- Rate limits
- Rate limits are applied at the organization level. ADE Parse endpoint: up to 100 pages per call (Playground: 100 pages; API: 100 pages). ADE Parse Jobs endpoint: up to 1 GB or 6,000 pages per job. Spreadsheets: up to 65,536 rows and 65,536 columns per file; CSV/XLSX up to 50 MB via API. Specific pages-per-hour limits vary by pricing plan but exact numbers are not published. [23]
- Known restrictions
- PDF parse via synchronous endpoint limited to 100 pages; larger documents require async Parse Jobs endpoint, Spreadsheet files limited to 50 MB via API (10 MB in Playground), Spreadsheet cells limited to 65,536 rows and 65,536 columns per file, Password-protected files require separate handling, EU and US deployments use separate API keys (not interchangeable), HIPAA compliance and Zero Data Retention (ZDR) available only on Team and Enterprise plans, Explore plan is single-user only, Free trial credits (1,000) expire 90 days after account creation, Text documents and presentations are converted to PDF before parsing, which may alter layout and page count, Custom processing pipelines are Enterprise-exclusive [24]
Developer surface
Integration
Adoption & maturity
- Launched
- 2025-05-28
- GA
- 2025-05-28
- Notable customers
- Barclays, Morgan Stanley, AstraZeneca, AbbVie, Deloitte, Toyota, Siemens Energy, Thermo Fisher, Qualcomm, Intel
Other OCR & Document Parsing APIs
Amazon Textract
"Automatically extract printed text, handwriting, layout elements, and data from any document"
Veryfi
"Documents into Data - securely, in seconds"
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."
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."
Nanonets
"AI Agents for Enterprise Data Processing."
Extend
"Turn documents into high quality data"
References
- ↑Description: landing.ai · landing.ai
- ↑Pricing model: landing.ai · docs.landing.ai
- ↑Published pricing: landing.ai · docs.landing.ai
- ↑Free tier: landing.ai · docs.landing.ai
- ↑Self-serve signup: prnewswire.com · landing.ai
- ↑Requires sales call: landing.ai
- ↑Enterprise plan: landing.ai · docs.landing.ai
- ↑Supported actions: docs.landing.ai · docs.landing.ai
- ↑Regions: landing.ai · landing.ai
- ↑Languages: docs.landing.ai · docs.landing.ai
- ↑Input types: docs.landing.ai
- ↑Output types: docs.landing.ai · landing.ai
- ↑Webhooks: docs.landing.ai
- ↑Sandbox: docs.landing.ai
- ↑SDK languages: github.com · github.com · docs.landing.ai
- ↑MCP server: docs.landing.ai
- ↑SOC 2: landing.ai · landing.ai · landing.ai
- ↑HIPAA: landing.ai · landing.ai · landing.ai
- ↑GDPR: landing.ai · landing.ai · landing.ai
- ↑ISO 27001: landing.ai
- ↑PCI DSS: landing.ai
- ↑Published SLA: landing.ai
- ↑Rate limits: docs.landing.ai · docs.landing.ai
- ↑Known restrictions: docs.landing.ai · docs.landing.ai · landing.ai
Change history
- 2026-06-15 Score Docs Quality: 25 → 45
- 2026-06-15 Score Agent Friendliness: 25 → 45
- 2026-06-14 Llms Txt URL: https://landing.ai/llms.txt → https://docs.landing.ai/llms.txt
- 2026-06-14 API Reference URL: (none) → https://docs.landing.ai/api-reference/tools/ade-parse
- 2026-06-14 Robots Allows Agents: (none) → Yes
- 2026-06-14 Has Structured Data: (none) → Yes
- 2026-06-14 Capabilities: {} → {"tables":true,"custom_models":true,"agentic_output":true,"receipts_invoices":t…
- 2026-06-14 Summary Md: (none) → LandingAI Agentic Document Extraction (ADE) is a REST API that converts PDFs, s…
- 2026-06-14 Score Docs Quality: 0 → 25
- 2026-06-14 Best For: Regulated or enterprise workloads - compliance attestations and an enterprise p… → Regulated or enterprise workloads - compliance attestations and an enterprise p…
- 2026-06-14 Score Agent Friendliness: 10 → 25
- 2026-06-14 Rendering: (none) → static
- 2026-06-14 Llms Txt Present: (none) → Yes
- 2026-06-14 Llms Txt URL: (none) → https://landing.ai/llms.txt
- 2026-06-14 Status Page URL: (none) → https://status.landing.ai
- 2026-06-14 Docs URL: (none) → https://docs.landing.ai
- 2026-06-14 Score Agent Friendliness: (none) → 10
- 2026-06-14 Scoring Methodology: (none) → Scores are computed deterministically from this profile's published, sourced fi…
- 2026-06-14 Avoid If: (none) → You want to try it free before paying
- 2026-06-14 Best For: (none) → Regulated or enterprise workloads - compliance attestations and an enterprise p…
- 2026-06-14 Score Trust Readiness: (none) → 55
- 2026-06-14 Score Procurement Friction: (none) → 85
- 2026-06-14 Score Docs Quality: (none) → 0
- 2026-06-14 Score Setup Speed: (none) → 55
- 2026-06-14 Score Pricing Transparency: (none) → 85
- 2026-06-14 Last Verified At: 2026-06-13T00:00:00.000Z → 2026-06-14T00:00:00.000Z
- 2026-06-14 SDK Packages: Python, Node.js → Python, Node.js
- 2026-06-14 Starting Price Usd: 1 → 1
- 2026-06-13 SLA Published: set to No
- 2026-06-13 Data Retention Policy URL: set to https://landing.ai/privacy-policy
- 2026-06-13 Documented Rate Limits: set to Rate limits are applied at the organization level. ADE Parse endpoint: up to 10…
- 2026-06-13 Known Restrictions: set to PDF parse via synchronous endpoint limited to 100 pages; larger documents requi…
- 2026-06-13 Auth Methods: set to api_key
- 2026-06-13 Auth Docs URL: set to https://docs.landing.ai/ade/ade-quickstart
- 2026-06-13 API Style: set to rest
- 2026-06-13 Base URL: set to https://api.va.landing.ai
- 2026-06-13 API Version: set to v1
- 2026-06-13 Versioning Scheme: set to url
- 2026-06-13 Quickstart URL: set to https://docs.landing.ai/ade/ade-quickstart
- 2026-06-13 Idempotency Supported: set to No
- 2026-06-13 Error Format: set to vendor-specific
- 2026-06-13 Requires Verification: set to No
- 2026-06-13 Starting Price Usd: set to 1
- 2026-06-13 Price Basis: set to 100 credits
- 2026-06-13 Free Tier Limit: set to 1,000 credits (expires 90 days after signup)
- 2026-06-13 Launched At: set to 2025-05-28
- 2026-06-13 GA Date: set to 2025-05-28
- 2026-06-13 Notable Customers: set to Barclays, Morgan Stanley, AstraZeneca, AbbVie, Deloitte, Toyota, Siemens Energy…
- 2026-06-13 Fields Not Found: set to mcp_server_available (LandingAI published a blog about MCP integration but no o…
- 2026-06-13 Source Confidence: set to high
Suggest an edit / leave a review
Leave a review or comment
curl -X POST https://apio.sh/api/feedback/landingai-ade \
-H 'Content-Type: application/json' \
-d '{"kind":"review","rating":5,"body":"Your experience with this API…"}'Suggest a correction to a field (cite a source)
curl -X POST https://apio.sh/api/suggest/landingai-ade/FIELD \
-H 'Content-Type: application/json' \
-d '{"value":"corrected value","citations":[{"url":"https://source.example/page","excerpt":"supporting quote"}],"note":"what changed and why"}'