Increased conversation latency using the Gemma 4 model

Update timeline

1. investigating Jul 30, 2026, 07:21 PM UTC

   We are investigating increased conversation latency affecting conversations using the Gemma 4 model. Conversations using other models are operating normally. We are actively working to identify the cause and will provide an update as soon as more information is available.

2. identified Jul 30, 2026, 07:31 PM UTC

   Our upstream model provider is rate- limiting a subset of requests for the Gemma 4 model, resulting in increased latency. We are routing traffic away from the affected capacity and working with the provider to restore normal performance.

3. resolved Jul 30, 2026, 08:02 PM UTC

   Conversation latency for the Gemma 4 model has returned to normal, and all traffic has been routed.