Benchmark-first: no numbers without a manifest — see the methodology
BiVelio Intake

Documents in. Verified data out.

Faster. More accurate. Lower cost. Proven on public and customer-specific benchmarks. Upload a business document and receive structured, validated data with field-level evidence.

No card · controlled retention · sample documents available
FasterBenchmark in progress
Time to Verified

P50 · P95 · verified intakes/min

More accurateBenchmark in progress
Strict Accuracy

critical-field escapes · review rate · evidence

Lower costBenchmark in progress
Cost per Verified Intake

GPU + APIs + retries + human review

Benchmarks and methodology

No numbers without a manifest.

Every future figure will open its dataset, hardware, date, commit and methodology, with downloadable results. Until real BiVelio-measured results exist, this page shows Benchmark in progress — never simulated numbers or pre-recorded demos presented as real.

OmniDocBench

Does it preserve text, layout, tables, formulas and reading order?

Benchmark in progress
ParseBench

Is the output useful for agents and workflows?

Benchmark in progress
RealDocBench

Do the concrete fields come out correct at comparable cost and latency?

Benchmark in progress
DocILE · VRDU · XFUND

Does it generalize across invoices, templates and languages?

Benchmark in progress
BiVelio IntakeBench

Does it win on the documents, languages and fields we sell?

Benchmark in progress
BiVelio LoadBench

What throughput and P50/P95 does the real hardware deliver?

Benchmark in progress
Track 01

Fully Automatic

No human intervention: the document goes in and the result is published exactly as it left the system, errors included.

Track 02

Verified Outcome

With review-by-exception included: what we would actually deliver in production, measured end to end.

Transparency: accuracy is always published together with Review Rate and Abstention Rate — never on its own.

How it works

Five steps, one CTA.

Describe what you need and the system picks the fastest route above the quality floor. Basic users never build schemas or pipelines, and engine names stay hidden on purpose.

01
Upload

PDF · image · email

02
Tell us

the fields you need or your business goal

03
Auto process

the fastest route above the quality floor

04
Verify

evidence + validators + exceptions

05
Deliver

JSON · export · webhook · BiVelio

Simplicity rule: a single CTA and zero mandatory configuration. Nobody needs to know which engine processed their document — only that the result arrived verified, with its evidence.

Try it with your documents

A benchmark that leaves the product running.

Seven steps, from first upload to activation. The same run works as benchmark, as onboarding and as a sales tool — with no extra steps.

  1. 01Upload 5–20 documentsreal ones, from your own operation
  2. 02Define the outcomewhat must come out the other end
  3. 03Describe the fields"name, NRT, date, total, IBAN and line items"
  4. 04See the evidenceevery value opens the exact snippet it came from
  5. 05Confirm the errorsyou decide what counts as a failure
  6. 06Receive the proofresults on your documents, not a demo
  7. 07Activate itthe same flow stays configured in production

One run, three jobs

  • Benchmark. Measured on your documents and with your error criteria, not on a dataset that flatters us.
  • Onboarding. By confirming the errors you have already configured the product: activating it is a click, not a project.
  • Sales tool. The final report is the evidence you can put in front of whoever signs.
Benchmark my documents

Initial scope, stated honestly: Supplier & Invoice Intake — invoices, purchase orders, receipts, credit notes, supplier bank forms and tax certificates — in ES · CA · EN · FR. We do not promise "any document".

Simple pricing

One unit. Four tiers. Zero surprise multipliers.

Everything is measured in Intake Units, and the tiers are published without figures on purpose: the number will arrive once it is measured, not before.

Intake Unit

One input processed to the agreed state. Classify, split, OCR, extract, validate and route never appear as surprise multipliers.

01

Free / Sandbox

To try the benchmark with no commitment.

  • Sample documents included
  • Limited volume
  • No card
02

Developer PAYG

Pay as you go, to build on top.

  • Intake Units on demand
  • API and webhooks
  • Transparent limits
03

Operate

The operations layer, as a separate tier.

  • Cases and policies
  • Approvals
  • Actions
04

Enterprise

Offered once implemented — not before.

  • Reserved throughput
  • Region and retention
  • SLA and support

Honesty note: definitive pricing is published only after measuring P95 variable cost and review exposure under real load.

Security and API

Evidence first. Unknown is a valid output.

A value without its evidence is a model's opinion, not data. Intake is built the other way round: proof first, schema second.

Evidence first

Every critical field opens its exact evidence: the snippet of the document the value came from.

Abstention rule

Unknown is a valid output — Intake never invents a value to complete a schema.

Isolation per schema

Each customer's data lives isolated per schema: no tables shared across tenants.

EU hosting

Data hosted and processed in the European Union, with retention controlled by contract.

API-first

JSON, export, signed webhooks and idempotent delivery: everything the UI does can be done via API.

Controlled retention

You decide how long we keep your documents — including the option of not keeping them at all.

Bring 5–20 documents. Leave with proof.

The benchmark runs on your documents and with your error criteria. No card, and with sample documents if you cannot share yours yet.

BiVelio Intake — Documents in. Verified data out.