EU AI ACTto the 2 December 2027 Annex III enforcement deadline.Check your tier →
Home · Models · Charaka 1.5
Sovereign model family · Healthcare

The clinical-documents model that never leaves the hospital.

Charaka is the healthcare family: tuned on clinical documentation, revenue-cycle and specimen-and-diagnostics workflows, and deployed inside the hospital's own data centre or private cloud. HIPAA-grade by architecture — PHI is processed where it already lives.

Live & Stable
Status
v1.5
Current version, frozen per deployment
4-bit
Quantised for your hardware
0
Outbound API calls
Live & Stable
Ch
MindMap Charaka 1.5
Named for Charaka, the physician whose Saṃhitā is a foundation text of Indian medicine.
Tuned for

Clinical documents · revenue cycle · specimen & diagnostics workflows

Clinical documentation

Discharge summaries, referrals and progress notes structured for the EHR — with the source passage cited on every extracted field.

Revenue-cycle automation

Coding suggestions, prior-authorisation packets and denial-appeal drafting from the chart, not from a template.

Specimen & diagnostics tracking

Orders, results and specimen chain-of-custody reconciled across lab, pathology and radiology systems.

Patient-services assistants

Scheduling, benefits and instruction Q&A grounded on the health system's own policies.

Runs where the data lives

Hospital data centre or private cloud — customer GPUs, customer identity provider, logs in the customer SIEM.

In production

Live and stable at a large US East-Coast hospital system, across revenue-cycle, diagnostics workflow and specimen tracking.

References are anonymised by default; named references on request under NDA.

Governance

What comes with every Charaka deployment

Provenance register

Base model, version and licence recorded for every deployment — the first artefact an auditor or a procurement team asks for.

Golden set per domain

Every family carries a curated evaluation set drawn from the document types its clients run on. Releases are gated on it.

Blind human + AI-judge scoring

Outputs scored by domain reviewers without knowing which model produced them, cross-checked by an AI judge. Raw runs available on request.

Frozen in production

The model that served your customers on Friday is the model serving them on Monday. No silent upgrades, no vendor deprecations, no pricing changes.

Plainly: Charaka is a domain fine-tune of a permissively-licensed open-weight base, not a from-scratch foundation model. The base, its version and its licence are recorded in the provenance register for every deployment.
Evaluate before you commit

Run Charaka on your own documents.

Send 20–50 representative documents or transcripts — anonymised is fine — and the acceptance rules your team uses today. We run Charaka 1.5 on infrastructure you control, score it against your criteria, and hand back the results and the harness. Two weeks, fixed scope, no production data.

An engineer replies within one business day. Evaluations run on infrastructure you control; we never ask for production data.

Talk to the product team