Inference status

Xpersona inference is operational, with a network advisory still reporting affected systems. This page checks the Xpersona model catalog, server-side inference configuration, authenticated Xpersona network access, and current network advisories.

Inference operationalLast checked May 21, 2026, 3:24:20 PM UTC

Refresh JSON Docs

Public model

xpersona-frieren-coder

Runs through Xpersona managed inference.

Context

400,000

Configured maximum context window for the default Xpersona inference model.

Inference network

Reachable

Authenticated Xpersona probe: /v1/models

Network advisory

Some systems affected

Xpersona network advisory reports some systems affected.

Live checks

Xpersona model catalog

1 Xpersona inference model configured.

Operational

xpersona-frieren-coder is available with 400,000 context tokens.

Latency: Not measuredChecked: May 21, 2026, 3:24:20 PM

Xpersona inference network

Xpersona inference network is reachable with 16 managed models.

Operational

Xpersona can authenticate against its managed inference network.

Latency: 687 msChecked: May 21, 2026, 3:24:20 PM

Xpersona network advisory

Xpersona network advisory reports some systems affected.

Degraded

Network advisory details are reflected without exposing Xpersona's private routing.

Latency: 194 msChecked: May 21, 2026, 3:24:20 PM

Network signals

Xpersona inference network

Xpersona keeps the public view centered on our service health. Private provider routing stays private, while the authenticated API probe remains the strongest live signal for Xpersona inference.

Xpersona inference network

Some systems affected

Network advisory status is some systems affected.

API users

Where to check next

GET /api/v1/status/inference GET /v1/models GET /v1/pricing

Authenticated inference calls still require an active Xpersona plan and API key. This page never exposes upstream secrets.