Document Intelligence and Decision Models in one place.
Nace.AI
Talk to salesSign inGet started

Perception series

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 startedTalk to sales
A tall arched window in a stone hall, its grid of panes framing Manhattan towers above a park, with plants along the sill and a figure on the steps below
ParsePOST /v1/parse
memo_1976-08-06.pdf
A 1976 internal memorandum with a handwritten note across the top right

Page 1 of 1 · 0 regions

0 of 9 blocks

    Trusted by

    • Intel
    • General Catalyst
    • Barton
    • Big Fouraccounting firm
    • Prosper
    • Mountain America Credit Union
    • CLA

    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.

    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.

    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

    Tables stay tables.

    Layout-aware Markdown with source locations.

    A painted willow bending over a still lake, its long branches hanging to the water and lilies along the near bank
    POST /v1/parseinvoice_2023T210.pdf
    POST /v1/splitap_packet.pdf

    Split

    One packet becomes the documents inside it.

    Page ranges for each document in a mixed upload.

    POST /v1/classifyinbox, 3 files

    Classify

    Labels come from your taxonomy.

    Document or page labels from your taxonomy.

    Extract

    Every field says found, not found or ambiguous.

    JSON Schema output, a status and a citation on every field.

    A painting of an old writing desk in afternoon sun by a curtained window, stacked with ledgers, loose papers and a typewriter, bookshelves on the wall beside it
    POST /v1/extractinvoice_2023T210.pdf

    Ground

    A location, not a judgment.

    Any quote resolved to its page, cells or span.

    A painted river winding through a wooded valley toward blue hills, tall pines on the bank and a pale sky above
    POST /v1/groundinvoice_2023T210.pdf

    Whatever the file, the answer points back.

    • A painted stack of loose papers on a grey table by a window, a magnifying glass resting on top
      POST /v1/groundinvoice.pdf

      Page and box

      PDF, Word, PowerPoint, images and scans, Visio

    • A painted stack of worn leather ledgers on a wooden table against a green wall
      POST /v1/groundtrial_balance.xlsx

      Sheet and cells

      Excel, CSV, XML, read cell by cell

    • A painted study at dusk, a brass lamp lit on a desk of papers and books, shelves of bound volumes behind it
      POST /v1/groundearnings_call.mp4

      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.

    1. A blurred evening street downtown, crowds and traffic streaming past tall buildings
      Where it runs
      Our cloud
      Network path
      Public TLS
      GPU tenancy
      Shared
      Updates
      Continuous

      Managed Cloud

      Start on our GPUs, behind our API, with a key from Console.

      • Shared GPU pool with strict tenant isolation
      • Public API over TLS, no training on your data
      • Usage-based pricing, no infrastructure to run

      For: pilots, evaluations, mid-market teams moving fast.

    2. A glass-walled conference room off an office hall, people passing in a blur on the other side of the glass
      Where it runs
      Our cloud
      Network path
      Private link
      GPU tenancy
      Dedicated
      Updates
      Continuous

      Dedicated Cloud

      Your own GPU cluster in our cloud, reached over private links instead of the public internet.

      • Single-tenant compute, pinned to your region
      • PrivateLink or VPC peering into your network
      • Customer-managed keys, dedicated throughput

      For: regulated teams that are cloud-first but done with shared infrastructure.

    3. A still lake at dawn closed in on every side by dark woods
      Where it runs
      Your cloud account
      Network path
      Inside your VPC
      GPU tenancy
      Dedicated
      Updates
      Pull from registry

      Your Cloud

      The platform installs inside your AWS or Azure account. Data stays within your boundary.

      • 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

      For: banks, Big 4 firms, anyone whose security review starts with “show us the network diagram.”

      Talk to sales
    4. An empty shore under a pale sky, the sea running out to a bare horizon
      Where it runs
      Your datacenter
      Network path
      None
      GPU tenancy
      Dedicated
      Updates
      Signed offline bundles

      On-Prem & Air-Gapped

      Your datacenter, your hardware, zero outbound.

      • 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

      For: government, defense, and sovereign environments where the network cable isn’t there.

      Talk to sales

    Send a file. Get every value back with its page.

    Get startedTalk to sales
    A painted marsh at sunset, pink and orange clouds over a still pond, wildflowers in the foreground and a stand of dark trees on the right