List Model Runtime Status

GET /admin/v1/models/status

List Model Runtime Status

Returns runtime routing and exclusion state for every model.

Parameters

Responses

• 200: OK
• [].cooldown_until (object, optional): Time when the current request-path cooldown expires. Omitted when the model is not in cooldown.
• allOf variant 1
• [].cooldown_until.nanos_since_epoch (integer, required): Nanosecond offset within the current second.
• [].cooldown_until.secs_since_epoch (integer, required): Whole seconds since the Unix epoch.
• [].display_name (string, required): Model alias used by proxy callers.
• [].id (string, required): Resolved model id. Direct-model runtime status is keyed by this id.
• [].kind (object, required): Whether the entry describes a direct upstream model or a routing model.
• allOf variant 1
• [].last_check_status (integer, optional): HTTP status code from the last background model check.
• [].last_checked_at (object, optional): Time of the last background model health check. Omitted before a check has completed.
• allOf variant 1
• [].last_checked_at.nanos_since_epoch (integer, required): Nanosecond offset within the current second.
• [].last_checked_at.secs_since_epoch (integer, required): Whole seconds since the Unix epoch.
• [].status (object, required): Runtime routing status for this model.
• allOf variant 1
• [].status_reason (string, optional): Reason for the current runtime status, when available.
• 401: Missing or invalid admin key
• error_msg (string, required): Human-readable error message.
• 500: Configuration store operation failed Response fields (application/json): identical to GET /admin/v1/models/status, response 401 above.

cURL

curl -X GET 'http://127.0.0.1:3001/admin/v1/models/status'