The short version
Cogneris is a multi-document, ReAct-architecture document AI platform with pay-per-page pricing, multi-LLM extraction, and a complete platform stack including review queues, per-field confidence and audit trail. Azure Document Intelligence is Microsoft's document extraction service inside Azure, now framed as a Foundry Tool and part of Azure Content Understanding. It has strong primitives and Microsoft 365 integration, with Azure OpenAI and Content Understanding for broader multimodal workflows.
Capability comparison
| Capability | Cogneris | Azure Document Intelligence |
|---|---|---|
| Product type | Complete platform — extraction, validation, workflows, audit trail | Foundry Tool / Azure service — extraction APIs and Content Understanding building blocks you compose into a workflow |
| Pricing model | Pay-per-page, includes review & audit features | Pay-per-page, additional Azure costs for storage / Key Vault / orchestration |
| Document classes | Tenant-configurable classification and zero-shot extraction | Pre-built models for invoices, receipts, ID, W-2, 1040, layout, general forms |
| LLM strategy | Multi-LLM (OpenAI + Anthropic), zero-retention configured | Azure OpenAI and Microsoft Foundry-native analyzers, including Content Understanding for broader content types |
| Workflow / orchestration | Built-in: review queues, validation rules, webhook callbacks, per-field confidence | Bring your own — Logic Apps, Functions, or external orchestrator |
| Custom model training | No model training: tenant-configurable classification and zero-shot extraction | Custom training in Document Intelligence Studio |
| Audit trail | Immutable per-request log with prompt hash, model version, response | Azure Monitor integration; you design the schema |
| Compliance | SOC 2 Type II readiness in progress, GDPR DPA, CCPA service-provider terms. HIPAA is out of scope for v1. | Inherits Azure's compliance posture (extensive) |
| Vendor lock-in profile | Standard REST API, portable schema | Azure ecosystem; portability requires migration work |
| Best fit | Teams that want a complete platform with batteries included | Teams deep on Azure that want raw building blocks |
When to choose which
Choose Azure Document Intelligence when…
- You're already on Azure and want a service that lives next to your IAM, Key Vault and data.
- You're standardising on Microsoft 365, Power Platform, or Azure AI Foundry — Azure DI integrates natively.
- You need Azure's specific compliance certs (FedRAMP, IL5, GovCloud) for federal workloads.
- You have engineers to assemble the platform — review UI, audit schema, orchestration — yourself.
Choose Cogneris when…
- You want a complete platform with review queues, validation rules, audit trail, and orchestration out of the box.
- You need multi-LLM across providers, not just Azure OpenAI.
- You want vendor-portable extraction that doesn't lock you into Azure.
- You need full audit lineage per request (prompt, model version, response) without a custom logging pipeline.
- You're embedding document AI in a product shipped on a different cloud than Azure.
Platform vs Foundry primitive
Azure Document Intelligence excels at the extraction primitive — pull structured data from a form or document, with strong accuracy on invoices and US tax forms. The 2026 positioning matters: Microsoft now routes buyers through Foundry Tools and Content Understanding, which broadens the story to multimodal analyzers and agent pipelines. That is powerful if your platform team wants Azure-native building blocks. Cogneris remains the faster path when you need review queues, validation rules, audit-trail schemas, alerting, and orchestration bundled into the product.
Azure prebuilt models vs Cogneris pages
As of July 2026, Azure Document Intelligence still positions prebuilt models as the fast path for common forms, while Azure Content Understanding expands the Microsoft story to complex, unstructured, and multimodal content. That is useful when the model matches the document exactly or your team wants Foundry-native analyzers. Cogneris maps the same buyer intent to document-specific pages, schemas, validation rules, review routing, and audit evidence.
| Azure prebuilt model intent | Cogneris target page | When Azure is enough | When workflow/review is needed |
|---|---|---|---|
| Invoice | Invoice extraction API | Single invoice parse into an Azure-native app. | AP approval, PO matching, duplicate checks, GL hints, ERP handoff. |
| Receipt | Receipt extraction API | Expense receipt field capture. | Policy review, duplicate detection, merchant normalization, T&E routing. |
| Bank statement | Bank statement extraction API | Statement text and transaction extraction. | Lending, reconciliation, multi-page stitching, reviewer evidence. |
| ID document | ID card OCR API | Basic identity field extraction. | KYC portals, proof-of-address checks, fraud signals, exception handling. |
| Tax and paystub forms | Tax form extraction / Payroll extraction | Known US tax/payroll forms. | Underwriting packets, income verification, audit-ready reviewer changes. |
| Mortgage documents | Mortgage document extraction | Azure-first loan document parsing. | Loan packets with multiple document types, missing evidence, and review state. |
| Layout and general document | Document parsing API | Raw layout extraction for an internal Azure pipeline. | Schema output, citations, validation, and workflow handoff. |
LLM strategy
Azure DI's LLM story is now broader than Azure OpenAI alone: Document Intelligence, Azure AI Foundry, and Content Understanding can work together in Microsoft-native agent and analyzer pipelines. Cogneris routes to OpenAI direct, Anthropic, or both, configurable per tenant. Customers who want provider failover or a non-Microsoft control plane find Cogneris easier to reason about. Customers happy on Azure OpenAI and Foundry get tighter integration from Azure DI.
Compliance & certifications
Azure's compliance footprint is comprehensive — FedRAMP, ISO 27001, SOC 2, HIPAA, IL4/IL5, GovCloud. Cogneris is currently SOC 2 Type II readiness in progress with GDPR DPA and CCPA service-provider framing; HIPAA is out of scope for v1. For federal or defense workloads requiring IL5+, Azure DI is the answer. For commercial enterprise workloads, Cogneris's posture is sufficient and broadening.
Azure Document Intelligence pricing, as published
The question most people bring to this page is what Azure Document Intelligence costs. The figures below are Microsoft's pay-as-you-go list prices for the S0 tier in the East US region, in US dollars, read from the Azure Retail Prices API on 11 November 2026. Prices differ by region and change without notice; Microsoft's pricing page is the source of truth, and the date here is the date we read it.
| Meter | List price (East US, USD) | What it covers |
|---|---|---|
| Read (OCR) | $1.50 per 1,000 pages, then $0.60 per 1,000 after the first 1 million pages in a month | Text and layout of printed and handwritten pages, no fields |
| Layout and prebuilt models | $10.00 per 1,000 pages | Layout, invoice, receipt, ID, W-2, 1098, health insurance card, contract, and the other prebuilt models |
| Custom extraction, custom generative | $30.00 per 1,000 pages | A model trained on your documents, or the generative variant |
| Custom classification | $3.00 per 1,000 pages | Routing each document to the right model |
| Query fields | $10.00 per 1,000 pages | Ad-hoc fields asked for on top of a model |
| Add-ons (high resolution, font, formula) | $6.00 per 1,000 pages, per add-on | Billed on every page the add-on runs on |
| Custom neural model training | $3.00 per hour | Beyond the included training hours |
| Free tier (F0) | 500 pages per month | No premium features; for evaluation |
Batch meters carry the same per-page prices as their synchronous counterparts.
Commitment tiers replace pay-as-you-go with a monthly fee for a page allowance, and overage above it. The Azure-hosted tiers published for East US:
| Commitment tier (Azure-hosted) | Monthly fee | Effective rate and overage |
|---|---|---|
| Prebuilt, 20,000 pages | $190 | $9.50 per 1,000 pages; overage $9.50 |
| Prebuilt, 100,000 pages | $900 | $9.00 per 1,000; overage $9.00 |
| Prebuilt, 500,000 pages | $4,000 | $8.00 per 1,000; overage $8.00 |
| Prebuilt, 1 million pages | $7,500 | $7.50 per 1,000; overage $7.50 |
| Custom, 20,000 to 1 million pages | $540 to $18,000 | $27.00 down to $18.00 per 1,000 |
| Read, 500,000 to 16 million pages | $375 to $7,200 | $0.75 down to $0.45 per 1,000 |
What the per-page price leaves out
At the extraction meter alone, Azure Document Intelligence is cheaper per page than Cogneris, and this page will not pretend otherwise. The comparison becomes fair only once the rest of the pipeline is priced: Azure Document Intelligence is a Foundry primitive, so storage, secrets, orchestration, validation, review and the audit trail are separate Azure services or your own code. Cogneris bills credits per operation and includes those pieces. The lines that usually appear on the invoice:
| Cost line | Cogneris | Azure Document Intelligence |
|---|---|---|
| Extraction | Credits per operation: classification 1 + 0.2 per page, extraction 2 + 1 per page. A 1-page document classified and extracted is 4.2 credits; Unlimited lists €0.02 per credit, so about €0.084 | The S0 meters above: $0.010 per page for a prebuilt model, $0.030 for a custom model, plus $0.003 to classify |
| Document storage | Included; retention is tenant-configurable and contract-specific | Azure Blob Storage: per GB-month, per 10,000 operations, plus egress |
| Secrets and keys | Included; encryption at rest with per-tenant keys where configured | Azure Key Vault: per 10,000 operations, more for HSM-backed keys |
| Orchestration | Built in: classification, extraction, validation rules, review queues, webhooks | Azure Functions or Logic Apps per execution, plus the code that chains them |
| Validation and human review | Included: validation rules, review queue with corrections kept, per-field confidence | Build it, or buy a separate review tool |
| Audit trail | Included: tamper-evident audit metadata on every run | Your own logging, storage, and retention design |
| Engineering time | A 7-day side-by-side evaluation on your documents, then a translation layer if you switch | Queueing, retries, monitoring, model selection, and the review UI, before the first document ships |
A worked example: 10,000 single-page invoices a month
- Azure Document Intelligence — the prebuilt invoice model at $10.00 per 1,000 pages is $100 a month at list, before Blob Storage, Key Vault, Functions or Logic Apps, the review tool, and the engineers who wire them together.
- Cogneris — 10,000 documents classified and extracted is 42,000 credits. The Scale plan covers 40,000 for €499 a month and the remaining 2,000 bill at €0.01 each, about €519 in total, with validation, the review queue, webhooks and the audit trail included. Our pricing page has the current plans and credit rates.
- What decides it — if your team already runs an Azure pipeline with review and audit solved, the meter price wins. If those pieces are still to be built, price the build. The extraction benchmark sets out how to run the same documents through both before you commit.
Switching considerations
If you're evaluating Cogneris against Azure Document Intelligence as your incumbent, the practical pieces matter:
- Schema portability — Cogneris emits clean JSON; if your pipeline already consumes Azure Document Intelligence's output, mapping is typically a one-day translation layer.
- Side-by-side evaluation — we run a 7-day evaluation against your real documents alongside your existing Azure Document Intelligence workflow. You get an accuracy and latency report you can show your CTO.
- No annual commit — start with a month-to-month plan, scale up as confidence builds. The pay-per-page pricing means you only pay for what you actually process.
For the full security and compliance posture, see our trust page. For pricing, see pricing. For a side-by-side evaluation against your current workflow, talk to our team.