Research statistics, verified

Statistics you can defend in front of a reviewer.

Celeus picks the correct statistical method for your dataset, runs it deterministically, and interprets the result - so the number in your manuscript is the number your data actually supports.

Provenance chain

Upload

De-identify

Analyze

Reproducible package

Every dataset carries this chain from the moment it lands to the moment it's cited. Nothing skips a step, and nothing is unverifiable after the fact.

What makes it trustworthy

Deterministic by construction

Every analysis is seeded, runs on pinned package versions, and emits a reproducible package: the plan, the exact R script, the seed, session info, and the audit log. If a run isn't bit-for-bit reproducible, that's a bug - not a caveat.

Read the validation report

No PHI ever reaches the model

One chokepoint stands between your data and the AI. It accepts only whitelisted metadata - never a data frame, never a row value. The model never sees a name, a date of birth, or a free-text field.

Research statistics, not a diagnosis

Celeus picks the correct statistical method, runs it, and flags problems - for research questions, on research data. It doesn't make patient-specific treatment calls, and it isn't meant to.

How it works

Upload

CSV or Excel, straight from your existing workflow.

De-identify

Identifier scan and redaction before anything else touches the data.

Analyze

The correct method, suggested and run - not guessed at.

Reproducible package

Script, seed, session info, and audit log - ready to defend.

Pricing

One researcher or a whole lab - the per-person price stays the same.

Free

See it work on your own data.

$0/mo

Start free

~15 AI actions
1 person
CSV / Excel import
De-identify, suggest, and run analyses

Pro

One researcher's full toolkit.

$19/mo

strictly one researcher - the audit trail attributes work to a person

Start Pro

Full analysis library
Reproducible packages
Priority AI allowance
Everything in Free

Built for labs

Team

A lab. Same price per person, plus the lab layer.

$19/mo per seat

per seat, minimum 3 seats, self-serve up to 25

Start a team

Shared workspace - the lab owns the data
Admin-managed membership & billing
Per-seat pooled allowances
Everything in Pro

Enterprise

The org wrapper around Team.

for organizations of 25+ seats, custom pricing

Everything in Team
SAML / SCIM SSO
Project-level access control
Org-wide audit view
Invoice / PO billing
Custom seats & quotas
Priority support
Deployment options on request

Need more tokens or runs without changing plans? Top-up packs: AI pack $15 for 1M tokens, Analysis pack $12 for 200 runs.

Out of storage? A storage top-up adds 25 GB added permanently, on any plan - no plan change and no seat change needed. Buy it from Settings > Billing; the price is shown before you pay.

Every plan above starts by signing in. If that does not let you through, request access and we will follow up by email.