Thanks — I’m responding to your question about whether there’s a live status for LiveKit Inference models. Short answer: No — we don’t currently provide a public live status page or a dedicated realtime availability API specifically for Inference models. What is available instead: • The LiveKit Cloud dashboard shows concurrency/usage limits by model type, so you can see how many model slots you’re using. (See: Introducing LiveKit Inference) • Agent observability gives session-level metrics (turn-by-turn latency, transcripts, inference traces) that help you spot performance or quality issues in your sessions. Those metrics can indirectly show model performance or availability for your usage. (See: Streamline troubleshooting with Agent Observability) • Dynamic routing to reroute inference requests based on latency/availability is planned (coming soon), which implies internal monitoring and smarter routing will be available in the future. If you’d like, I can help with next steps: • Explain where to find concurrency/usage info in your dashboard. • Walk through how to use agent observability to detect model performance problems for your sessions. • Gather details about your use case (expected concurrency, region, models used) so I can suggest monitoring strategies or mitigation patterns. Which of those would you like to do next? Sources: Introducing LiveKit Inference: A unified model interface for voice AI | Liv... | Streamline troubleshooting with Agent Observability | LiveKit