--- title: "Nace Document Intelligence" description: "Nace Document Intelligence parses, splits, classifies, extracts and grounds 36 file types with a location on every value. First on grounding and level with the frontier models on split and extract in Nace's Perception evaluation, managed, in your cloud or air-gapped." canonical: "https://nace.ai/ndi" updated: 2026-10-07 --- # Nace Document Intelligence > Nace Document Intelligence parses, splits, classifies, extracts and grounds 36 file types with a location on every value. First on grounding and level with the frontier models on split and extract in Nace's Perception evaluation, managed, in your cloud or air-gapped. ## Introducing Nace Document Intelligence Five tools that parse, split, classify, extract and ground any of 36 file types, and point every value back to the page it came from. Ranks first on grounding against frontier models. Available in the Console today. - [Get started](https://console.nace.ai?utm_campaign=document-intelligence-launch&utm_content=ndi&utm_medium=website&utm_source=nace.ai) - [Talk to sales](https://nace.ai/contact?product=perception) Example parse jobs in the Console: `POST /v1/parse`. Archives: memo_1976-08-06.pdf, a 1976 internal memorandum with a handwritten note across the top right. Page 1 of 1 · 9 regions. ```markdown # MEMORANDUM August 6, 1976 **TO:** All Concerned · **FROM:** R. Vance _I agree completely_ 8/6/76 For some time, the Research Department has been concerned… Accordingly, we are recommending the discontinuance of the A & B service… If you feel that we should continue to subscribe… R.V. cc: Research, Media, Brand Group, Planning… ``` Banking: operating_statement_2026-05.pdf, a business bank statement for May 2026 with a long transaction table. Page 1 of 2 · 7 regions. ```markdown # Business Banking Statement 62, 01 May 2026 to 31 May 2026 BIC XXXXXXXXXXX | Sort code 00-00-00 ## Statement of Account - Operating GBP **Account name** Operating Company Ltd. · **IBAN** GB00 XXXX 0000 0000 0000 00 | Opening | Money in | Money out | Closing | | Date | Reference | Description | Debit | Credit | Balance | ``` Payroll: pay_stub_2023-11-20.pdf, a semi-monthly pay stub with earnings, taxes and deductions tables. Page 1 of 2 · 10 regions. ```markdown # EXAMPLE CORP **Pay Period:** 11/01/2023 - 11/15/2023 ## EMPLOYEE INFORMATION **Employee Name:** Sample Employee · **SSN:** XXX-XX-0000 **Pay Rate:** $7,500.00 Monthly · **Filing Status:** Single | Description | Hours | Rate | Current | YTD | | Federal Income Tax | 644.20 | 6,706.80 | | 401(k) 5% | 212.50 | 2,212.50 | | Gross Pay | Total Taxes | Total Deductions | Net Pay | | YTD Gross | YTD Taxes | YTD Deductions | YTD Net Pay | ``` Filings: form_10-k_fy2023.pdf, the cover page of an annual report on Form 10-K. Page 1 of 146 · 6 regions. ```markdown # UNITED STATES SECURITIES AND EXCHANGE COMMISSION ## FORM 10-K ☒ ANNUAL REPORT PURSUANT TO SECTION 13 OR 15(d)… Commission File Number 000-00000 **EXAMPLE COMPANY** · Delaware · I.R.S. No. 00-0000000 | Title of each class | Trading Symbol(s) | Exchange | ``` Construction: payment_application_2022-10.pdf, a construction application and certification for payment. Page 1 of 2 · 6 regions. ```markdown # APPLICATION AND CERTIFICATION FOR PAYMENT **TO OWNER:** Example Holdings LLC · **FROM:** Example Contractor LLC | 3. CONTRACT SUM TO DATE | $2,136,322.00 | | Description | Additions | Deductions | The undersigned Contractor certifies that to the best of… **AMOUNT CERTIFIED** $386,084.93 ``` ## Leading performance at a fraction of the cost. Our most accurate setting reads documents as well as the best tool we tested, for less than half the price. Our lightest setting is the cheapest of them all and still beats all but one of the leading AI models. Chart: Parse Index against cost per 1,000 pages. Each run is named beside its company mark. The line is the Pareto frontier: no other run is both cheaper and more accurate than a run on it. Cost is on a log scale, so the best trade-off sits top left. | Model | Parse Index | OmniDocBench | ParseBench Content Faithfulness | USD / 1,000 pages | | --- | ---: | ---: | ---: | ---: | | NDI High | 0.820 | 92.6 | 91.16 | 6.50 | | LlamaParse Agentic | 0.820 | 89.4 | 91.78 | 13.80 | | GPT-6 Astra (low) | 0.813 | 89.6 | 90.67 | 70.57 | | NDI Low | 0.805 | 93.8 | 89.05 | 2.70 | | LlamaParse Cost Effective | 0.799 | 87.4 | 89.87 | 3.80 | | Mistral OCR 4 | 0.796 | 89.2 | 89.55 | 4.00 | | Anthropic Opus 4.7 | 0.787 | 88.2 | 90.26 | 71.40 | | Databricks Parse (high) | 0.784 | 90.3 | 88.25 | 6.12 | | Chandra-2 (Datalab) | 0.773 | 88.6 | 83.70 | 10.00 | | Extend AI v1 | 0.766 | 85.9 | 84.59 | 6.00 | | GPT-5.6 Terra | 0.766 | 89.1 | 82.56 | 15.51 | | Azure DI | 0.762 | 86.3 | 84.93 | 10.00 | | Reducto Parse | 0.744 | 83.1 | 86.37 | 30.00 | Parsing leaderboard export, 15 September 2026. Cost is USD per 1,000 pages as measured. ParseBench is scored on its main metric, Content Faithfulness, only. ## Five tasks. One job contract. ### Parse `POST /v1/parse`. Tables stay tables. Layout-aware Markdown with source locations. ### Split `POST /v1/split`. One packet becomes the documents inside it. Page ranges for each document in a mixed upload. ### Classify `POST /v1/classify`. Labels come from your taxonomy. Document or page labels from your taxonomy. ### Extract `POST /v1/extract`. Every field says found, not found or ambiguous. JSON Schema output, a status and a citation on every field. ### Ground `POST /v1/ground`. A location, not a judgment. Any quote resolved to its page, cells or span. ## Whatever the file, the answer points back. - Page and box: PDF, Word, PowerPoint, images and scans, Visio - Sheet and cells: Excel, CSV, XML, read cell by cell - Span and timestamp: Text, HTML, email, audio and video ## One platform. Four boundaries. Same models, same API, same serving stack at every tier. The only thing that changes is the boundary around your data, from our cloud to your metal. Your data trains your models. The weights, adapters and eval sets stay yours, inside the boundary you pick. | Attribute | Managed | Dedicated | Your Cloud | Air-Gapped | | --- | --- | --- | --- | --- | | Where it runs | Our cloud | Our cloud | Your cloud account | Your datacenter | | Network path | Public TLS | Private link | Inside your VPC | None | | GPU tenancy | Shared | Dedicated | Dedicated | Dedicated | | Updates | Continuous | Continuous | Pull from registry | Signed offline bundles | ### Managed Cloud Start on our GPUs, behind our API, with a key from Console. For: pilots, evaluations, mid-market teams moving fast. - Shared GPU pool with strict tenant isolation - Public API over TLS, no training on your data - Usage-based pricing, no infrastructure to run ### Dedicated Cloud Your own GPU cluster in our cloud, reached over private links instead of the public internet. For: regulated teams that are cloud-first but done with shared infrastructure. - Single-tenant compute, pinned to your region - PrivateLink or VPC peering into your network - Customer-managed keys, dedicated throughput ### Your Cloud The platform installs inside your AWS or Azure account. Data stays within your boundary. For: banks, Big 4 firms, anyone whose security review starts with “show us the network diagram.” - Runs in your VPC with your keys, your logs, your IAM - Updates pull from our registry; nothing flows back out - The deployment model our audit and banking customers run in production [Talk to sales](https://nace.ai/contact?product=cloud&source=developers) ### On-Prem & Air-Gapped Your datacenter, your hardware, zero outbound. For: government, defense, and sovereign environments where the network cable isn’t there. - No egress, no telemetry, offline license activation - Signed offline update bundles on your schedule - Ships as software on your servers or as a pre-configured appliance [Talk to sales](https://nace.ai/contact?product=cloud&source=developers) ## Send a file. Get every value back with its page. - [Get started](https://console.nace.ai?utm_campaign=document-intelligence-launch&utm_content=ndi&utm_medium=website&utm_source=nace.ai) - [Talk to sales](https://nace.ai/contact?product=perception) ## For agents - [Drex API guide](https://nace.ai/drex.md): the decision model: request shape, question types, benchmarks and deployment, as markdown - [Decision endpoint](https://console.nace.ai/v1/systemone): POST with model "drex-latest", a state string and typed questions (choice, noul, score); https://console.nace.ai/v1/models lists checkpoints - [Document endpoints](https://console.nace.ai/v1/documents/{parse|split|classify|extract|ground}): POST a source (a public URL, an uploaded workspace file or a finished parse job) and poll GET https://console.nace.ai/v1/documents/jobs/{id}; the same key and credit as decisions - [Console](https://console.nace.ai): API keys, the playground, usage and billing; send `Authorization: Bearer $NACE_API_KEY` on every request - [Console docs](https://console.nace.ai/docs): quickstart, question types, the document routes, errors, limits and pricing - [Nace Document Intelligence](https://nace.ai/ndi.md): the Perception series: parse, split, classify, extract and ground any file type with a location on every value - [Developers](https://nace.ai/developers.md): Console: what it holds, a scripted agent session, the ways in and the four deployment boundaries, from our managed cloud to air-gapped - [Site index](https://nace.ai/llms.txt): every page on nace.ai; append `.md` to any page URL or send `Accept: text/markdown` for the markdown version