Model selection, proven
Anyone can serve a model.
We prove why this one was chosen.
A model gateway hands you an answer. It can't hand your auditor a record of why that model was the right one for the task. Pick a task below — watch the sovereign router weigh the candidates, choose, and seal a portable selection receipt you can re-verify offline, with nothing of ours in the trust path.
Choose a task to route
Why a selection receipt, not just an answer
A model gateway is judged on the answer. A governed one is judged on the decision behind it. When a regulator asks why a model was used on a PHI workflow — or why a cheaper model was acceptable, or why a request was kept in-boundary — “the router picked it” is not an answer an auditor can re-check. A signed selection receipt is. It travels with the work, re-verifies offline at lockedinlabs.ai/verify, and it's signed with the same key as the model's own passport — one provenance authority across the whole decision.
POST /api/router/select { "scenario": "clinical-summary" }
→ { receipt: { format:"governed-receipt/v1", algorithm:"Ed25519",
body:{ statement:"selection/v1", ... }, signature, public_key } }
POST /api/verify-selection <the receipt>
→ { verified: true } # same Ed25519 math as lockedinlabs.ai/verifyHow proving model selection works
Why a signed selection receipt is different from an opaque routing decision — and how anyone can re-verify the choice offline.
Does LeanLogix prove which model was selected and why?
Yes. The Sovereign Router classifies a request, scores the routable catalog on capability, cost, latency, and availability, and serves the chosen model only after re-verifying its Ed25519 passport at request time. The selection is sealed into a portable, signed selection receipt — so the choice of model is itself an offline-verifiable record, not an opaque routing decision. That selection-proof is the headline differentiator: anyone can serve you a model; LeanLogix proves why this one was chosen.
What is a signed model passport?
A model passport is a signed AI bill of materials for a release — base model, datasets and exclusions, eval probes, the approver, and an Ed25519 signature over the verbatim bytes. Because it is signed over the bytes, an auditor recomputes the fingerprint offline with curl and a public key and gets the result rather than your word. A model selection can also carry a portable selection receipt that re-verifies at the central public verifier, lockedinlabs.ai/verify, with nothing of LeanLogix's in the trust path.
How is a model foundry different from a fine-tuning platform or an inference host?
A generic fine-tuning platform hands you a model on a shared, metered plane; a hyperscaler model service keeps it inside their cloud and meters every token. LeanLogix is built the other way: a model forked per customer, served inside your boundary with no external token meter, and shipped with a signed AI bill of materials you can re-verify offline. The differentiator is governance and provenance — proving why a model was chosen and what went into it — not raw GPU inference, which LeanLogix rides on top of.
What is LeanLogix?
LeanLogix is a private model foundry and model-governance control plane. It trains and fine-tunes small models on open foundations (the Qwen2.5 family), then governs the full lifecycle — registry, evals, separation-of-duties release, and a signed model passport. It is the management plane that rides on top of inference, not an inference or GPU host itself. LeanLogix is built by LockedIn Labs for regulated, in-boundary teams in healthcare and finance.