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

- Provider: [Groq](https://down.guide/providers/groq)
- Confidence: Confirmed
- Impact: Degraded
- lasted 1h 15m
- started 2025-12-24 23:01 UTC
- id: DWN-6a264f9327
- Official page: https://groqstatus.com/incidents/01KD99GZ8D8KKBW1TDDRP9D2KJ

## Updates from Groq
### 2025-12-24 23:01 UTC: identified
We’ve identified an issue causing 503s for the llama-3.3-70b-versatile production model. We’ve started mitigation. Error rates are improving, but some requests may still fail while we continue tuning and monitoring.

### 2025-12-25 00:04 UTC: monitoring
We have implemented a fix for llama-3.3-70b-versatile and performance is improving. The team is continuing to work the issue and we hope to have it resolved shortly.

### 2025-12-25 00:16 UTC: resolved
The issues affecting llama-3.3-70b-versatile have been resolved. The model is operating normally. We apologize for the disruption and thank you for your patience.

From the builder: does your app depend on Groq? [Sazabi](https://www.sazabi.com/?utm_source=down-guide&utm_medium=markdown&utm_content=groq) detects problems in your own logs without hand-written monitors, and you can ask it in plain language which errors mention Groq.

---
down.guide reads providers' official status pages every minute and adds its own evidence, always labeled. Free, no account. Agents: MCP at https://down.guide/mcp, REST at https://down.guide/api/v1, feeds at https://down.guide/feed. Built by [Sazabi](https://www.sazabi.com/?utm_source=down-guide&utm_medium=markdown&utm_content=DWN-6a264f9327), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards.