[Metrics Endpoint] 5xx Errors on */metrics/discovery
The /metrics/discovery endpoint returned 5xx errors. This affected metrics endpoints and the Console and Index Management components. Pinecone reports that the incident is resolved. It lasted 93 minutes.
State
Resolved
Started
Lasted
1 h 33 min
Worst impact
Degraded
Timeline
4 updatesInvestigating
1 h 24 min 90%
Identified
3 min 3%
Monitoring
6 min 6%
Updates
Times in UTCAs posted by Pinecone
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
*/metrics/discovery endpoint is receiving 5xx errors. Impacting metrics endpoints (Datadog, Prometheus, etc.)
Affected components
2Pinecone in the last 90 days
Full historyIncidents in 90 days
9
Days with an incident
10
Median duration
1 h 10 min
This incident
1.3× the median
Other Pinecone incidents
All incidentsPinecone·[Pod-Based Indexes] Stalled control plane operations.
Pinecone reports stalled control plane operations on Pod-Based Indexes. The problem affects Index Management. Pinecone made a fix and monitored the result. The incident is resolved and lasted 3 hours and 19 minutes.
Pinecone·[Inference] 5xx errors on some `llama-text-embed-v2` requests
Incident is resolved.
Pinecone·[SERVERLESS][GCP][us-central1] Newly created indexes failing to initialize
This incident has been resolved.
Pinecone·[Pods][AWS][us-east-1] Write failures and high latency
The third party dependency recovered, this incident has resolved.
Pinecone·[Serverless][AWS][eu-west-1] 5xx on read requests
This incident has been resolved.
Follow Pinecone
Your coding agent knows when Pinecone is down, and tells you when a failure is theirs, not yours. You can also get Pinecone 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 "pinecone" and tell me if Pinecone 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=pinecone/feed subscribe https://outages.cc/feed.xml?providers=pineconeFAQ
Go from tracking outages to fixing production issues with Polylane.
Try Polylane