Checking endpoint…Shows whether the Unvault model inference endpoint is reachable and serving. The indicator reads a cached snapshot — it does NOT probe HF on every poll (that would prevent the endpoint from scaling to zero and burn budget). States: checking (initial probe), offline (unreachable), presumed cold (no activity in 15+ min, or model not listed), loading / warming (~30–90 s cold-start), and warm (model serving — confirmed by a real request). Send any inference request to refresh.
Welcome back

Sign in to Labs

This is an internal workspace for the Unvault team. Sign in with your @unvault.co Google account to access the inspection, search, annotation, and model tools.

Continue with Google

Restricted to @unvault.co accounts.

Identifier = subscriber UUID or subscriber name (the rainfall auth endpoint accepts either).

Trouble signing in? Ping Navya or the Pragma Digital team.