Live  /  Groq  /  Incident

Groq: Model Performance or Availability Issue: llama-3.3-70b-versatile

Groq · groq.comMinor incidentResolved2025-12-25 00:16 UTC
Public — what happened

Summary

Groq reported a minor problem with its llama-3.3-70b-versatile production model beginning at 23:01 UTC on December 24, 2025, during which some requests to the model failed with 503 errors. The company said it had pinpointed the issue and begun working to reduce it, with failures declining but not yet eliminated. Groq applied a fix by 00:04 UTC on December 25 and continued watching as performance recovered, then declared the issue resolved at 00:16 UTC with the model running normally. Groq did not publicly describe what caused the errors.

Timeline

Source of record: provider status page. Summary written by SquidGrid from the provider’s published updates; times in UTC.

Independent path health

The status page is the symptom. SquidGrid measures the paths that reach Groq against their own baselines — whether the routes carrying your traffic degraded, at which handoff, and who owns that stretch.

🔒 Sign in to see
Customers get the live Provider Assessment Report for Groq: its full incident track record, what tends to break, and recent public reports of problems.

Included with any paid plan.

Open the Groq report →

More from Groq

The full archive is on the Groq status & history page.

Related: Groq status & history. SquidGrid is not affiliated with Groq.