Looking for an update now? Check the current status, or follow Tavus for future changes.
89.5%of 38 verified observed days had no reported provider issue
90-Day Trend
Dashed calendar markers below identify legacy observations whose source-at-observation was not recorded.
Monthly Status Summary
Month
Issue-free days
Days Tracked
Days with issues
September 2026
86.7%
30
4
This percentage summarizes normalized provider-status observations by calendar day. It is not duration-based, component-weighted, or contractual uptime. See the methodology and limitations.
Recorded Daily Status (Last 91 Days)
Jul 3Today
Legacy observation Operational Degraded Partial Outage Major Outage Maintenance No Data
Our upstream GPU provider has applied a mitigation and gemma-4 error rates have returned to normal. We have alternate routing paths staged and ready to enable if the issue recurs. We are monitoring before marking this resolved.
identified
We've confirmed the issue originates with our GPU provider, who has declared a networking incident on their side. We're testing mitigations to route gemma-4 traffic elsewhere. Conversations using other LLMs are unaffected. If you need stability now, you can point your persona at a different LLM.
identified
The issue is isolated to our default LLM (gemma-4), served by a GPU provider that began returning errors at 17:40 UTC. As a temporary mitigation we are routing gemma-4 traffic to an alternate model. Customers on gemma-4 may notice a change in response style while this is in effect; we will revert once the provider recovers.
identified
This is affecting gemma-4; we recommend our customers switch to a different LLM for immediate needs.
investigating
Starting at 17:40 UTC, conversations using our default LLM began experiencing long delays and unresponsive replicas. A GPU provider is returning errors and our automatic failover is recovering most turns, but with significant added latency. We are routing traffic to a backup provider.
investigating
It appears this issue is coming from one of our downstream providers, Crusoe. We're continuing to investigate full scope of conversations affected.
investigating
We are aware of an issue currently impacting tavus conversations, we are investigating.
Legacy Incident Archive
16 archived records restored. These records predate source-at-observation attestation. They are shown as historical ServiceAlert records only and do not establish a provider-reported incident, resolution, duration, or current active state.
May 2026
Some conversations not starting
minorSource not attested
Last archived state: resolved
View archived record details
monitoring
A fix has been implemented and we are monitoring the results.
investigating
We are investigating an infrastructure issue that is causing some conversations not to start
April 2026
Increased error rates with perception models
minorSource not attested
Last archived state: resolved
View archived record details
monitoring
Raven-0 and Raven-1 are now operating normally, and we are actively monitoring the system to ensure continued stability.
identified
The issue was identified and a fix has been deployed
investigating
We are investigating increased error rates with Raven-0 and Raven-1
Intermittent Call Connection Issues
Source not attested
Last archived state: resolved
View archived record details
monitoring
There are intermittent call connection issues tied to upstream Daily and Cloudflare outages.
Daily: https://status.daily.co/
Cloudflare: https://www.cloudflarestatus.com/
Replica takes longer to join in some conversations
minorSource not attested
Last archived state: resolved
View archived record details
investigating
We are currently investigating this issue.
Elevated Error Rate When Joining Conversations
majorSource not attested
Last archived state: resolved
View archived record details
monitoring
A fix has been released by the Daily team, we are seeing traffic return to normal and will be continuing to monitor
identified
We are seeing elevated API errors from our webRTC provider Daily
https://status.daily.co/incidents/0vkhkxd7m20b
Conversations not properly initiating
minorSource not attested
Last archived state: resolved
View archived record details
monitoring
A sub GPU provider has encountered a <10 minute outage involving their AWS instance. Traffic was automatically rerouted, although some conversations which were already sent to this provider did not properly join.
All traffic is now performing within SLA, and we're continuing to monitor.
investigating
Conversations requests are succeeding, but encountering issues at the GPU level which are causing replicas to not properly join
