Infrastructure facts for enterprise procurement and security teams evaluating LandingAI Agentic Document Extraction (ADE).
Deployment Options
| Deployment | Available at | Data location |
|---|---|---|
| Hosted SaaS, US | All plans | AWS US (Ohio) |
| Hosted SaaS, EU | All plans | AWS EU (Ireland) |
| Containerized app in your VPC | Enterprise | Your AWS, Azure, or GCP |
| On-premises | Enterprise | Your own infrastructure |
VPC: ADE maintains zero data retention because it runs on your VPC. Your organization is responsible for retention controls on your infrastructure and on any subprocessors you integrate.
EU: a separate environment with region-specific API keys. All data is stored and processed within the EU. Pricing is the same in the US and EU regions.
Snowflake: Parse and Extract are available as stored procedures. Files process on LandingAI's hosted service, so organizations with ZDR requirements should call the API directly. See the Snowflake app overview.
Scale and Processing
ADE processes documents synchronously or as asynchronous jobs.
- Synchronous returns the result inline. Suited to interactive workflows where a person or agent is waiting.
- Asynchronous jobs accept substantially larger documents and much longer processing windows. A full legal discovery set, actuarial filing, or medical records packet runs as a single job with no pre-splitting.
- Output delivery is either inline in the response or written directly to a presigned URL in storage you control, on S3, Azure Blob, or GCS.
Rate limits apply per organization and scale by plan: standard on Explore, higher on Team, priority on Enterprise. For current page counts, file size caps, and timeouts, see Rate Limits.
Cost Transparency
- Asynchronous jobs default to a lower-cost service tier. Synchronous requests run at the standard rate.
- Every response reports the credits consumed and the counts behind that charge, so any invoice line reconciles against the response you received.
- Credits apply to successful and partially successful requests.
- For current rates, see Credit Consumption. For plans, see Plans & Billing.
SLAs and Support
- SLA and uptime guarantees: Enterprise plan. Uptime percentage and remediation terms are set in the Enterprise agreement. Request current terms through the contact page.
- Support tiers: community on Explore, enhanced on Team, dedicated on Enterprise.
- Also on Enterprise: priority rate limits, custom processing pipelines, and SSO through SAML 2.0 and OpenID Connect.
Compliance and Data Governance
- SOC 2 Type II: independently audited. Reports and system status in the Trust Center.
- GDPR: supported through the EU deployment on AWS Ireland, where data is stored and processed within the EU.
- HIPAA: requires ZDR enabled plus a signed BAA, both available on Team and Enterprise. The BAA request goes through Organization Settings once ZDR is active.
- ZDR behaviour: with the ZDR option enabled, customer data is not persisted beyond processing. Your data is used exclusively to perform the operation you request, and processing ends when the output is returned to you. LandingAI does not use your data for training or improving its models when ZDR is active.
- ZDR scope: covers the entire platform including all subprocessors. It applies to direct API calls and the client libraries, and a separate setting extends it to the Playground.
- ZDR and asynchronous jobs: once enabled, ZDR covers every call regardless of how the document is submitted.
Integration Paths
- REST API callable from any language, with official Python and TypeScript libraries.
- Cloud storage through presigned URLs on S3, Azure Blob, and GCS, for both document input and output delivery, so your pipeline keeps the storage layer.
- Output as Markdown for RAG pipelines, plus a structured tree carrying page reference and bounding box grounding on every element.
- Snowflake lands parsed output in Snowflake tables, queryable with SQL and available to Cortex Search and Cortex Analyst. See the Snowflake app overview.
Production Evidence
- Eolas Medical: ADE was integrated into the Eolas Medical platform, used by over 400 medical centers including Stanford Hospital, Massachusetts General Hospital, and more than 80% of acute NHS hospitals in the UK. Reported outcomes: 100% source attribution for all answers, 90% reduction in time spent searching for clinical information, and zero configuration required for deployment across 400+ sites.
- Global Tier-1 bank: KYC and Client Due Diligence on multi-lingual corporate documents of 200 to 300 pages per client, integrated with an existing KYC platform on the bank's own VPC. Reported a 40% to 60% reduction in manual document review time and hundreds of analyst hours saved per week.
- Autyn: mortgage loan origination across thousands of issuers without template configuration. Reported 94% to 98% field-level accuracy, end-to-end income extraction cut from one to two hours of human work down to one to three minutes, across 500 or more loan files and 3,000 or more documents in production.
FAQ
Does ADE offer formal uptime SLAs?
Yes, on the Enterprise plan. The uptime percentage and remediation terms sit in the Enterprise agreement.
Can ADE handle multi-hundred-page filings or patient record packets?
Yes. Asynchronous jobs accept large documents in a single call with no pre-splitting. For current page and size limits, see Rate Limits.
Can ADE run inside our own infrastructure?
Yes, as a containerized application in your VPC on AWS, Azure, or GCP, or on-premises. Both are available on Enterprise.
What compliance certifications does ADE hold?
SOC 2 Type II, with reports in the Trust Center. GDPR through the EU deployment. HIPAA on Team and Enterprise, with ZDR enabled and a signed BAA in place.
How do we keep documents off LandingAI infrastructure?
Deploy to your own VPC or on-premises. On hosted SaaS, enable ZDR and use presigned URLs for both input and output, so documents move from your storage back to your storage.
Is ADE pricing different in the EU?
No. Pricing is the same in the US and EU regions. See Plans & Billing.