Provider incident title: “llama3.1-8b API Latency Degraded”
Started
Wednesday, May 6, 2026
03:40 PM UTC
Duration
4m
total
Resolved
03:45 PM UTC
May 6, 2026
Affected
Tickerr's independent monitoring detected service recovery. API checks returned successful responses.
Independent monitoring detected elevated API latency for llama3.1-8b. Current TTFT is 2.1× above the rolling p50 baseline (446ms vs p50 208ms). The service is responding but slower than normal. Tickerr measures time-to-first-token via live streaming API calls every 5 minutes.
Cerebras is back online
View current status and uptime history
Cerebras 30-day uptime: 100% based on Tickerr's independent monitoring checks.
This incident was automatically detected by Tickerr's HTTP monitoring probes. Tickerr checks Cerebras every few minutes from multiple regions. An incident is opened after 3 consecutive failed probes to reduce false positives.
This incident lasted 4m and affected llama3.1-8b.
Tickerr monitors 90+ AI tools independently. View live Cerebras status or all AI tool status.
Get alerted next time Cerebras goes down
Tickerr monitors 90+ AI tools. We'll email you when an incident starts or resolves.
Weekly AI pricing & uptime digest
Price drops, new model releases, and incident summaries - every Monday. Free.
Also on Tickerr