Planned Maintenance: meta-llama/llama-4-maverick-17b-128e-instruct (me-central-1)
**When:** Monday, Nov 3, 2025 • 00:00 to 03:00 UTC (Sunday, Nov 2, 16:00 to 19:00 PT) **What** • We’re performing planned maintenance on the me-central-1 deployment of **meta-llama/llama-4-maverick-17b-128e-instruct** to keep systems current. Other regions remain available. **Impact** • No customer action required. • Requests that explicitly target the me-central-1 endpoint for this model will be unavailable for approximately 2 hours within the window, possibly longer if troubleshooting is required. • Requests not pinned to me-central-1 will continue to be served by other regions. **Updates** • We will post at start, after the change completes, and when monitoring finishes.
The latest update from Groq.
State
Scheduled
Started
373 d ago
2025-10-24 18:25 UTC
Ongoing for
373 days
Worst impact
Maintenance
Timeline
1 updateScheduled
373 days 100%
Updates
Times in UTCAs posted by Groq
**When:** Monday, Nov 3, 2025 • 00:00 to 03:00 UTC (Sunday, Nov 2, 16:00 to 19:00 PT) **What** • We’re performing planned maintenance on the me-central-1 deployment of **meta-llama/llama-4-maverick-17b-128e-instruct** to keep systems current. Other regions remain available. **Impact** • No customer action required. • Requests that explicitly target the me-central-1 endpoint for this model will be unavailable for approximately 2 hours within the window, possibly longer if troubleshooting is required. • Requests not pinned to me-central-1 will continue to be served by other regions. **Updates** • We will post at start, after the change completes, and when monitoring finishes.
Groq in the last 90 days
Full historyIncidents in 90 days
3
Days with an incident
2
Median duration
23 min
This incident
Not comparable
Other Groq incidents
All incidentsGroq·Model Performance or Availability Issue
The issues affecting **minimaxai/minimax-m2.7** have been **resolved**. The model is operating normally. Root cause: **hardware connectivity issues**. We apologize for the disruption and thank you for your patience.
Groq·GroqCloud Console Errors Affecting Multiple Regions
The **Groqcloud console issue has been resolved**. All services are operating normally. We apologize for the disruption and **appreciate your patience**.
Groq·Model Performance or Availability Issue - minimaxai/minimax-m2.7
The issues affecting **minimaxai/minimax-m2.7** have been **resolved**. The model is operating normally. Root cause: **Data center hardware issues**. We apologize for the disruption and thank you for your patience.
Follow Groq
Your coding agent knows when Groq is down, and tells you when a failure is theirs, not yours. You can also get Groq incidents in a feed reader or in Slack.
Install the outages.live MCP server, so that when something breaks you can tell if the cause is a provider we depend on and not my code. It reads the official status pages of cloud, AI, payment and developer providers and gives you their incidents as MCP tools.
Add it as a remote MCP server named "outages" at https://outages.cc/mcp (Streamable HTTP, no authentication), with your CLI command or your MCP config file.
Then:
1. Make sure it connects and shows the tools get_provider, list_feed and send_feedback.
2. Call get_provider with "groq" and tell me if Groq has a problem right now.
3. From now on, when a call to a third-party service fails or becomes slow, call get_provider for that service before you change my code.Paste this into any coding agent. It adds the server with its own MCP setup.
https://outages.cc/feed.xml?providers=groq/feed subscribe https://outages.cc/feed.xml?providers=groqFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane