# LandingAI Agentic Document Extraction (slim)

> LandingAI's Agentic Document Extraction is a hosted API that parses PDFs, images, Office files and spreadsheets into Markdown with page coordinates, then extracts fields against a JSON schema. Python and TypeScript libraries and a CLI call it.

- Full: https://www.anchorterminal.com/tools/landingai-agentic-document-extraction.md (~8,750 tokens) · this version ~1,930 tokens · JSON https://www.anchorterminal.com/tools/landingai-agentic-document-extraction.json · canonical https://www.anchorterminal.com/tools/landingai-agentic-document-extraction
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-10

**B · 69/100 · rank #199 of 950 · #3 in Document parsing & extraction · not agent-ready · confidence medium**


Assessment: Parse, Extract and Ground have a public OpenAPI description, Markdown docs, published credit rates and page limits, and a status page showing no incident in 90 days. The Explore plan's single API key cannot be revoked without support, and the published terms let LandingAI train on customer documents unless Zero Data Retention, a Team and Enterprise setting, is on.

## Facts

- Kind: HTTP API · vendor: LandingAI, Inc. · category: Document parsing & extraction · legal entity: LandingAI, Inc. · provenance 76/100
- Endpoint: `https://api.ade.landing.ai` (HTTP)
- Auth: API key · pricing: Pay per use · x402: no · licence: Proprietary service under LandingAI's terms for Agentic Document Extraction. The Python and TypeScript libraries and the CLI are Apache-2.0, and the skills repository is MIT
- Probe metrics: not measured yet (probes haven't run)
- APIs: Gen2 at `/v2` with nine operations (Parse, Parse Jobs create, list and get, Extract, Extract Jobs create, list and get, Ground), OpenAPI 3.1. Gen1 at `/v1/ade` adds Classify, Section and Split, all in Preview, and Build Extract Schema
- Hosts: US `https://api.ade.landing.ai` (AWS us-east-2), EU `https://api.ade.eu-west-1.landing.ai` (AWS eu-west-1). Keys are specific to one region
- Models: DPT-3 Pro (default) and DPT-3 Verity (Preview, for digitally created text documents), selected by dated snapshot, `-latest` alias or family name
- File types: PDF, images, DOCX, PPTX, ODT, RTF, XLSX and CSV on Gen2. Password-protected files and legacy DOC and PPT need Gen1
- Page references: A bounding box for every block, line or word boxes through atomic grounding, and Ground maps each extracted field to block ids, pages and boxes (vendor's description)
- Rate limits: Explore 100 pages a minute on priority and 6,000 pages an hour on standard. Team 200 and 12,000. Enterprise custom. Per organisation and per model family. A lower standard limit applies during the free trial
- Size limits: Synchronous 50 MiB and the plan's per-minute page limit. Jobs 1 GiB for PDFs and 6,000 pages a PDF on the standard tier
- Processing time: Synchronous parse times out at 475 seconds. Jobs time out at 6 hours. Turnaround times are estimates, not guarantees
- Free tier: 1,000 free credits on the Explore plan, no card needed
- Plans: Explore pay as you go at $0.01 a credit, one user. Team from $250 a month with 25,000 to 200,000 credits a month. Enterprise custom, with SLA, SSO, IP allowlist, VPC and on-premises deployment
- Webhooks: Signed events for finished Parse and Extract jobs under the Standard Webhooks specification (HMAC-SHA256), retried for roughly 12 hours
- Data retention: Zero Data Retention on Team and Enterprise. Unfetched job results are deleted 24 to 48 hours after completion. Retention without it is not stated in the reviewed documentation
- Libraries: Python `landingai-ade` 1.18.1 and TypeScript `landingai-ade` 2.13.1 (both 17 September 2026), Apache-2.0. `ade` CLI 1.0.5 (7 August 2026), Apache-2.0, with usage telemetry that `ADE_TELEMETRY=0` or `DO_NOT_TRACK` turns off
- Certifications: SOC 2 Type II, HIPAA with a BAA, and GDPR compliance, per landing.ai/security-at-landingai (vendor's claims, reports not read)
- Status: status.landing.ai on Instatus, with US and EU components for Agentic Document Extraction and an incident history feed
- Prices: Credit (Explore and Team plans) $0.01 per credit; DPT-3 Pro parse, standard tier, typical business page $15 per 1,000 pages; Team plan, smallest credit pack $250 per month (plan)

- Scores: Reliability 85, Performance pending, Schema & documentation 88, Agent ergonomics 75, Security & auth 43, Payments & pricing 40, Task success pending, Maintenance & community 85, Transparency & trust 63 · total over the 7 assessed categories
- Why: Reliability, Graded as a hosted API. · Schema & documentation, Public OpenAPI 3.1 description of the nine Gen2 operations, and a second for Gen1 (25). · Agent ergonomics, Graded on the HTTP API. · Security & auth, Bearer key in a header, never in the URL. · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, The API changelog's latest entry is 22 September 2026, and the Python and TypeScript libraries were tagged on 17 September (30). · Transparency & trust, Closed service under published terms, with Apache-2.0 libraries and CLI (15 of 30).
- Sources: 30, open questions: 9, both in the full twin
- Capabilities: docs.parse, docs.extract, docs.tables, docs.ocr, docs.chunk, docs.classify
- JSON: https://www.anchorterminal.com/api/v1/tools/landingai-agentic-document-extraction.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/landingai-agentic-document-extraction.svg` or a link to https://www.anchorterminal.com/tools/landingai-agentic-document-extraction from a page on landing.ai or one of its subdomains, or the README of github.com/landing-ai/ade-python, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Send `Authorization: Bearer <key>` to `https://api.ade.landing.ai/v2/parse`. EU keys work only on `https://api.ade.eu-west-1.landing.ai`
2. Submit large files to `/v2/parse/jobs`. Synchronous parse times out at 475 seconds and is capped at the plan's pages-per-minute limit
3. Leave jobs on the `standard` tier unless speed matters. It consumes half the credits of `priority`
4. Run Extract on the Markdown that Parse returned, then call Ground for page numbers and boxes. Ground consumes no credits
5. On a 429, read the message. One case clears with backoff and the other means the document is too large for the tier

## Connect

```bash
pip install landingai-ade
```

```bash
curl -X POST 'https://api.ade.landing.ai/v2/parse' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'document=@document.pdf' \
  -F 'model=dpt-3-pro-latest'
```

```bash
/plugin marketplace add landing-ai/ade-document-processing-skills
/plugin install ade-document-processing@ade-document-processing-skills
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/landingai-agentic-document-extraction

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Extend API + MCP | B | 62.9 | docs.parse, docs.ocr, docs.extract, docs.tables, docs.chunk, docs.classify | https://www.anchorterminal.com/tools/extend.min.md |
| Reducto API + MCP | B | 62.9 | docs.parse, docs.ocr, docs.extract, docs.tables, docs.chunk, docs.classify | https://www.anchorterminal.com/tools/reducto.min.md |
| LlamaParse API + MCP | C | 59.2 | docs.parse, docs.ocr, docs.extract, docs.tables, docs.chunk, docs.classify | https://www.anchorterminal.com/tools/llamaparse.min.md |
| Google Cloud Document AI | BB | 73.9 | docs.parse, docs.ocr, docs.extract, docs.tables, docs.chunk | https://www.anchorterminal.com/tools/google-cloud-document-ai.min.md |
| Unstructured API + MCP | D | 46.9 | docs.parse, docs.ocr, docs.extract, docs.tables, docs.chunk | https://www.anchorterminal.com/tools/unstructured.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)