Increased conversation latency using the Gemma 4 model
minor- Started
- Jul 30, 3:21 PM EDT
- Resolved
- Jul 30, 4:02 PM EDT
- Duration
- 41 min
Tavus's updates (3)
- investigating · Jul 30, 3:21 PM EDT
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.
- identified · Jul 30, 3:31 PM EDT
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.
- resolved · Jul 30, 4:02 PM EDT
Conversation latency for the Gemma 4 model has returned to normal, and all traffic has been routed.
What our checks recorded
We checked Tavus 8 times from Tavus's start time to its resolution, once every five minutes. Every one of them reached Tavus's site, so this incident did not show up as a failed page load. Our check loads the public site; it cannot see an API error or a broken feature. Median response time was 138 ms, against 155 ms over the 24 hours before. Tavus posted the incident at Jul 30, 3:21 PM EDT.
Updates are Tavus's own words from its status page (status: resolved); we never add an inferred cause. The vendor's incident page ↗