Every inference backend for the requested model is unhealthy or circuit-broken. Operational, not a code defect.
{ "type": "https://docs.cortex.foundation/problems/no_capacity", "title": "No capacity for this model right now", "status": 503, "code": "no_capacity", "request_id": "req_…"}
See Errors for how to branch, and what not to render from detail.
⌘I
Assistant
Responses are generated using AI and may contain mistakes.