outages.live
Live

Pinecone

Pinecone is operational

Checked 2 min ago Operational

History

90 days agoToday

Incidents in 90 days

7

Days with an incident

8

Median duration

58 min

Longest incident

11 h 7 min

Components

26

Pod Indexes

us-west1-gcp Operational
90 days agoNo incidentsToday
us-east1-gcp Operational
90 days agoNo incidentsToday
us-central1-gcp Operational
90 days agoNo incidentsToday
us-west4-gcp Operational
90 days agoNo incidentsToday
us-east4-gcp Operational
90 days agoNo incidentsToday
us-west1-gcp-free Operational
90 days agoNo incidentsToday
us-west4-gcp-free Operational
90 days agoNo incidentsToday
gcp-starter Operational
90 days agoNo incidentsToday
eu-west1-gcp Operational
90 days agoNo incidentsToday
eu-west4-gcp Operational
90 days agoNo incidentsToday
asia-southeast1-gcp Operational
90 days agoNo incidentsToday
asia-northeast1-gcp Operational
90 days agoNo incidentsToday
asia-southeast1-gcp-free Operational
90 days agoNo incidentsToday
northamerica-northeast1-gcp Operational
90 days agoNo incidentsToday
eastus-azure Operational
90 days agoNo incidentsToday
us-east-1-aws Operational
90 days ago1 day with an incidentToday
Console Operational
90 days ago1 day with an incidentToday
Index Management Operational
90 days ago2 days with an incidentToday
Inference Operational
90 days agoNo incidentsToday
Assistant Operational
90 days ago1 day with an incidentToday

Serverless Indexes

AWS us-west-2 Operational
90 days ago1 day with an incidentToday
AWS us-east-1 Operational
90 days agoNo incidentsToday
AWS eu-west-1 Operational
90 days ago2 days with an incidentToday
Azure eastus2 Operational
90 days agoNo incidentsToday

Past incidents

Provider status pageTimes in UTC

Oct 14, 2026

Duration1 min14:48 to 14:48[Inference] 5xx errors on some `llama-text-embed-v2` requestsDegraded

Incident is resolved.

Oct 7, 2026

Duration1 h 10 min20:40 to 21:49[SERVERLESS][GCP][us-central1] Newly created indexes failing to initializePartial outage

This incident has been resolved.

Sep 28, 2026

Duration8 min04:13 to 04:20[Pods][AWS][us-east-1] Write failures and high latencyDegraded

The third party dependency recovered, this incident has resolved.

Sep 22, 2026

Duration58 min23:34 to 00:32[Serverless][AWS][eu-west-1] 5xx on read requestsPartial outage

This incident has been resolved.

Sep 17, 2026

Duration11 h 7 min05:37 to 16:44[Serverless][AWS][us-west-2] 5xx errors on the readpathPartial outage

This incident has been resolved.

Sep 1, 2026

Duration4 h 36 min15:04 to 19:405xx errors on some control plane operationsPartial outage

This incident has been resolved.

Aug 25, 2026

Duration21 min15:50 to 16:11[SERVERLESS][GCP][us-central1] 5xx errors on some read and write requestsPartial outage

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.

Prompt
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.live/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.

RSS
https://outages.live/feed.xml?providers=pinecone
Slack
/feed subscribe https://outages.live/feed.xml?providers=pinecone

Go from tracking outages to fixing production issues with Polylane.

Try Polylane