sevanalysis

Pinecone

AI. Source: Pinecone status page.

Incidents, last 90 days
7
Median to mitigation
31m
Median to resolution
58m
p95 to resolution
11h 7m
Naming an upstream provider
85%
With a postmortem on the status page
0%

What failed, last 90 days

The text does not say enough to tell5
A provider or third-party service this vendor depends on failed2

Tagged by deepseek/deepseek-v4.1-flash from each incident's updates. See the methodology.

Incidents per month

All recorded incidents

[Inference] 5xx errors on some `llama-text-embed-v2` requests minor 2026-10-14 14:48 UTC 0m

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).

  1. resolved

    Incident is resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[SERVERLESS][GCP][us-central1] Newly created indexes failing to initialize major 2026-10-07 20:40 UTC 1h 10m

Affected: Index Management

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Pods][AWS][us-east-1] Write failures and high latency minor 2026-09-28 04:07 UTC 14m

Affected: us-east-1-aws

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by deepseek/deepseek-v4.1-flash with medium confidence (taxonomy v0.3).

Names an upstream provider: AWS.

  1. identified

    A shared dependency is having issues. Determining mitigation

  2. resolved

    The third party dependency recovered, this incident has resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][eu-west-1] 5xx on read requests major 2026-09-22 23:34 UTC 58m

Affected: AWS eu-west-1

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).

Names an upstream provider: AWS.

  1. identified

    The issue has been identified and mitigation is being actioned. A small percentage of read requests are impacted.

  2. monitoring

    We have mitigated the errors and are monitoring to ensure there is no reoccurrence.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] 5xx errors on the readpath major 2026-09-17 05:37 UTC 11h 7m

Affected: AWS us-west-2

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with low confidence (taxonomy v0.3).

Names an upstream provider: AWS.

  1. investigating

    We have identified the issue and we are in the process of mitigating.

  2. monitoring

    We are recovering and are monitoring to ensure no further errors occur.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

5xx errors on some control plane operations major 2026-09-01 15:04 UTC 4h 36m

Affected: Console, Index Management, Assistant

Failure mode: A provider or third-party service this vendor depends on failed. Root cause: A failure at a provider or vendor they depend on. Tagged by deepseek/deepseek-v4.1-flash with medium confidence (taxonomy v0.3).

Names an upstream provider: Google Cloud.

Started during Google Cloud: Multiple products in us-central1-b are experiencing network service degradation..

  1. investigating

    We are currently investigating this issue.

  2. investigating

    This is likely related to ongoing issues in GCP. Affected services include Console, Index management, Assistant management, and APIs served at api.pinecone.io

  3. monitoring

    Error rates have subsided, we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[SERVERLESS][GCP][us-central1] 5xx errors on some read and write requests major 2026-08-25 15:50 UTC 21m

Affected: GCP us-central1

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[SERVERLESS][Azure][eastus2] 5xx errors for some namespaces critical 2026-07-21 19:10 UTC 30m

Affected: Azure eastus2

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).

Names an upstream provider: Azure.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[SERVERLESS][AWS][us-east-1] Increased latency and 5xx errors for some indexes minor 2026-07-20 16:44 UTC 1h 15m

Affected: AWS us-east-1

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Increase in freshness lag for some namespaces minor 2026-07-12 23:21 UTC 4h 55m

Affected: AWS us-east-1

Failure mode: Data delayed, stale, lost or corrupted, or needing replay after recovery. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with medium confidence (taxonomy v0.3).

Names an upstream provider: AWS.

  1. investigating

    We are observing freshness lag affecting a small number of indexes in AWS us-east-1, resulting in some queries not serving fresh data. We are actively investigating.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][Azure][eastus2] 5xx errors on some requests for some indexes major 2026-07-09 09:50 UTC 4h 47m

Affected: Azure eastus2

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by deepseek/deepseek-v4.1-flash with high confidence (taxonomy v0.3).

Names an upstream provider: Azure.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Some initial queries to infrequently read namespaces incorrectly returning empty results minor 2026-06-18 10:00 UTC 8h 23m

Affected: AWS us-west-2, AWS eu-west-1, Azure eastus2, GCP us-central1, GCP europe-west4

  1. investigating

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Metrics tab in the console not showing graphs none 2026-06-16 13:05 UTC 4h

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] 5xx errors for some requests on some indexes major 2026-06-06 17:05 UTC 3h 35m

Affected: AWS us-west-2

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] Read path operations for some indexes may experience elevated latency and timeouts minor 2026-06-06 13:05 UTC 2h 45m

Affected: AWS us-west-2

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[AWS][us-east-1] 5xx errors for some requests on some indexes minor 2026-06-06 00:48 UTC 27m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. investigating

    We are continuing to investigate this issue.

  3. identified

    The issue has been identified and a fix is being implemented.

  4. monitoring

    A fix has been implemented and we are monitoring the results.

  5. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] 5xx errors and longer response times on upsert requests for some indexes. major 2026-05-25 13:41 UTC 1h 19m

Affected: AWS us-west-2

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[AWS][us-east-1] 5xx errors on read and write operations for some indexes major 2026-05-13 20:14 UTC 1h 1m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[AWS][us-east-1] 5xx errors for some requests on some indexes major 2026-05-06 20:02 UTC 27m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Pinecone Console loading slowly for some users minor 2026-05-06 15:00 UTC 20m

Affected: Console

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    The hosting provider for app.pinecone.io experienced increased errors and latency starting at 15:00 UTC. At 15:15 UTC, they implemented a fix and are continuing to monitor the impact. This incident did not impact Pinecone APIs or services.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[GCP][europe-west4] Errors for upsert operations on some indexes major 2026-03-13 08:50 UTC 1h 3m

Affected: GCP europe-west4

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[AWS][us-east-1] Prometheus metrics are unavailable through the Pinecone console or the metric proxy minor 2026-03-05 21:57 UTC 1h 5m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] 5xx errors on some read operations for some indexes major 2026-03-04 21:06 UTC 1h 10m

Affected: GCP us-central1

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[GCP][us-central1][europe-west4] Errors on some read operations major 2026-02-23 23:14 UTC 2h 38m

Affected: GCP us-central1, GCP europe-west4

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    The impact was related to a Google Cloud Storage incident (Event ID: WDVVRMB).

  3. identified

    The issue has been identified and a fix is being implemented.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Increase in freshness lag for some namespaces minor 2026-02-05 10:55 UTC 11h 2m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on read operations for some indexes major 2026-01-15 12:12 UTC 3h 18m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Intermittent unavailability across all environments for some indexes major 2026-01-02 16:31 UTC 1h 27m

Affected: us-west1-gcp, Console, AWS us-west-2, us-east1-gcp, AWS us-east-1, us-central1-gcp, AWS eu-west-1, us-west4-gcp, Azure eastus2, us-east4-gcp, GCP us-central1, us-west1-gcp-free, GCP europe-west4, us-west4-gcp-free, gcp-starter, eu-west1-gcp, eu-west4-gcp, asia-southeast1-gcp, asia-northeast1-gcp, asia-southeast1-gcp-free, Index Management, northamerica-northeast1-gcp, Inference, eastus-azure, Assistant, us-east-1-aws

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] 5xx errors on some read path operations major 2025-12-31 03:13 UTC 16m

Affected: AWS us-west-2

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] Partial control plane unavailability for some users none 2025-12-19 01:15 UTC 0m

Names an upstream provider: Google Cloud.

  1. resolved

    From 8:15 PM to 8:50 PM UTC, some users experienced partial control plane unavailability.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][europe-west4] 5xx errors on read and write operations for some indexes major 2025-12-15 10:39 UTC 11h 23m

Affected: GCP europe-west4

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Increased file processing time for Assistant minor 2025-12-09 20:15 UTC 5h 35m

Affected: Assistant

  1. investigating

    Files uploaded to an assistant may take longer than expected to appear in chat and context requests during this time.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Unavailability for embed and rerank requests none 2025-12-08 20:43 UTC 0m

  1. resolved

    From 3:43 PM EST to 3:50 PM EST, some embed and rerank requests were unavailable.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] 5xx errors on some read operations for some namespaces major 2025-12-05 18:36 UTC 2h 6m

Affected: GCP us-central1

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] 5xx errors on read path operations for some namespaces major 2025-12-03 15:53 UTC 46m

Affected: AWS us-west-2

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on some read path operations major 2025-11-24 17:28 UTC 1h 2m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Some index-level usage metrics unavailable none 2025-11-13 02:00 UTC 0m

  1. resolved

    Index-level usage metrics were unavailable for approximately 24 hours beginning at around 9:00 PM EST on November 12th

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][eu-west-1] 5xx errors on some write path operations major 2025-11-06 14:38 UTC 2m

Affected: AWS eu-west-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Partial unavailability on cohere-rerank-3.5 model none 2025-10-30 22:00 UTC 0m

Affected: Inference

  1. resolved

    From 4:58 PM EST to 5:10 PM EST, the cohere-rerank-3.5 model experienced partial unavailability.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] 5xx errors on some read and write operations major 2025-10-23 17:32 UTC 51m

Affected: GCP us-central1

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. investigating

    We are continuing to investigate this issue.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][Azure][eastus2] 5xx errors on some read and write operations major 2025-10-21 17:57 UTC 1h 27m

Affected: Azure eastus2

Names an upstream provider: Azure.

  1. investigating

    We are currently investigating this issue.

  2. identified

    The issue has been identified and a fix is being implemented.

  3. monitoring

    A fix has been implemented and we are monitoring the results.

  4. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Some users may be unable to access the Pinecone web console. All API services remain fully operational. major 2025-10-21 01:27 UTC 2h 3m

Affected: Console

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Some users may be unable to access the Pinecone web console. All API services remain fully operational. major 2025-10-20 17:05 UTC 55m

Affected: Console

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] `403 PermissionDenied` errors for read and write operations on some indexes and assistants minor 2025-09-15 15:52 UTC 6m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. monitoring

    A fix has been implemented and we are monitoring the results.

  2. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on some read and write operations major 2025-09-10 13:16 UTC 3h 22m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] 5xx errors on some read operations major 2025-09-10 12:52 UTC 4h 30m

Affected: AWS us-west-2

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on write operations for some indexes major 2025-09-09 12:55 UTC 1h 45m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on read operations for some indexes major 2025-09-02 22:46 UTC 15h 14m

Affected: AWS us-east-1

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Console stuck loading after login for some users minor 2025-08-29 20:28 UTC 2h 14m

Affected: Console

  1. investigating

    We are investigating an issue where some users are unable to access the console after logging in. Affected users may see the console stuck in a loading state. The issue is related to elevated errors from our authentication provider.

  2. monitoring

    The loading issue has recovered, and we are continuing to monitor.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] Unavailability for some read path operations for some indexes major 2025-08-28 18:30 UTC 1h 55m

Affected: AWS us-west-2

Names an upstream provider: AWS.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][europe-west4] Indexing lag on some indexes; recent writes may not appear in reads minor 2025-08-26 13:22 UTC 1h 43m

Affected: GCP europe-west4

Names an upstream provider: Google Cloud.

  1. investigating

    We are currently investigating this issue.

  2. monitoring

    A fix has been implemented and we are monitoring the results.

  3. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] Unavailability for some read path operations for some indexes major 2025-08-21 16:54 UTC 1h

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on read operations for some indexes major 2025-08-11 21:29 UTC 24m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-west-2] Unavailability for some read path operations major 2025-08-05 16:17 UTC 1h 6m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Unavailability for some read path operations major 2025-08-01 14:22 UTC 5h 24m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] 5xx errors on read operations for some indexes major 2025-07-31 22:16 UTC 16h 40m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1][eu-west-1] Unavailability for some read and write path operations major 2025-07-31 09:42 UTC 29h 14m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Read units not included in API response for query, list, and fetch operations on serverless indexes minor 2025-07-16 19:27 UTC 4d 15h

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on read operations for some indexes major 2025-07-15 22:00 UTC 59m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on read operations for some indexes critical 2025-07-15 20:13 UTC 18h 7m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][eu-west-1] 5xx errors on read operations for some indexes major 2025-06-24 00:26 UTC 31m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors on read operations for some indexes major 2025-06-22 21:47 UTC 5h 58m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][Azure][eastus2] 5xx errors on some read path operations major 2025-06-17 13:22 UTC 36m

Names an upstream provider: Azure.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Google Cloud outage impacting all GCP clusters, Inference, Assistant, and control plane operations; console elements failing to load major 2025-06-12 17:55 UTC 8h 9m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][eu-west-1] Increase latencies and error rates on read endpoints major 2025-06-11 13:45 UTC 10h 21m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][eu-west-1] Increase latencies and error rates on read endpoints major 2025-06-11 11:55 UTC 1h 32m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][europe-west4] Increased latencies and timeouts on query operations for some indexes minor 2025-06-09 17:05 UTC 53m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Index creation and deletion operations delayed in Azure eastus2 serverless environment major 2025-06-08 22:47 UTC 19h 33m

Names an upstream provider: Azure.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][eu-west-1] Delayed availability of newly-written records on some indexes minor 2025-06-04 16:58 UTC 5h 9m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS eu-west-1][GCP europe-west4] Internal server errors for read path operations on some indexes minor 2025-05-30 22:47 UTC 2h 2m

Names an upstream provider: AWS, Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][europe-west4] Increased latency and timeouts on some indexes, read operations impacted minor 2025-05-28 17:25 UTC 7h 41m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Indexing lag on some indexes; recent writes may not appear in reads minor 2025-05-28 02:25 UTC 25m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] Sporadic errors for fetch and query operations on some indexes minor 2025-05-23 19:06 UTC 11h 3m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved

Excerpts are shortened. Read the full incident on Pinecone's status page.

Availability issues with rerank endpoint major 2025-05-23 04:00 UTC 0m

  1. resolved

    We saw availability issues with `rerank` endpoints across all models due to disruptions in our rerank hosting infrastructure. The issue is resolved now and stable.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Partial Control Plane Outage major 2025-05-16 09:05 UTC 2h 25m

  1. resolved

    This incident has been resolved

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][Azure][eastus2] High indexing lag on some indexes minor 2025-05-15 13:30 UTC 3h 11m

Names an upstream provider: Azure.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Increased latency on read path requests for some indexes minor 2025-05-15 08:22 UTC 14h 4m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Inference] Downtime on llama-embed & multilingual-e5-large models critical 2025-05-14 03:15 UTC 0m

  1. resolved

    From 11:10 PM EST to 11:25 PM EST, the models multilingual-e5-large & the llama-text-embed-v2 were down. The incident is now resolved. We are continuing to monitor and are working on an RCA.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] 5xx errors and increased latency for some read operations on some indexes major 2025-05-07 17:20 UTC 35m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] Increased latency for upsert and fetch operations on some indexes minor 2025-05-06 11:04 UTC 5h 38m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][Azure][eastus2] 5xx errors on read requests to some indexes major 2025-05-05 15:48 UTC 36m

Names an upstream provider: Azure.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Errors on queries for some indexes major 2025-05-05 11:16 UTC 2h 5m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Elevated P90 latencies in file upload and search none 2025-05-02 23:45 UTC 42m

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Elevated latencies on file ingestion in Assistant (US) minor 2025-04-28 08:30 UTC 6h 15m

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Assistant] File uploads and deletions not processing major 2025-04-25 15:03 UTC 17m

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [us-east-1] Delays in index creation and deletion operations major 2025-04-24 11:41 UTC 52m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][GCP][us-central1] 500 errors on queries for some indexes major 2025-04-23 09:00 UTC 3h 50m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] gRPC status code 14 (503 errors) on some queries minor 2025-04-10 02:43 UTC 23m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][Azure][eastus2] Increased latency and 5xx errors on upserts major 2025-04-09 14:56 UTC 36m

Names an upstream provider: Azure.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Newly created indexes failing to initialize major 2025-03-25 11:38 UTC 1h 17m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

API requests to records (Pinecone Inference) endpoints failing with 404 error in GCP and Azure serverless environments critical 2025-03-10 17:45 UTC 6h 5m

Names an upstream provider: Azure, Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[GCP-Starter] Increase in write operations errors and an increase in freshness lag. minor 2025-03-10 17:04 UTC 27d 19h

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved. As communicated via email, all indexes in the gcp-starter environment must be migrated to serverless.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [us-central1] Increase in latency for all operations minor 2025-02-21 06:02 UTC 6h 32m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Metrics in console not populating for serverless indexes minor 2025-02-18 17:44 UTC 3h 3m

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [eu-west-1] Increased latency and 5xx errors on write path minor 2025-02-11 19:51 UTC 11m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [eu-west-1] Increased latency and 5xx errors on write path minor 2025-02-11 14:30 UTC 20m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [us-central1] Increased latency and errors on write and fetch operations major 2025-01-28 16:22 UTC 46m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [us-central1] Increased freshness lag for some indexes minor 2025-01-15 17:33 UTC 26h 30m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Increased latency and 500 errors for queries major 2025-01-09 22:49 UTC 1m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [ europe-west4] 504 errors for read operations minor 2024-12-20 10:11 UTC 1h 17m

Names an upstream provider: Google Cloud.

  1. resolved

    Since the resources on the read path have increased, no new errors have been observed. This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [us-central1] Elevated error rates and latencies for some operations minor 2024-12-19 08:27 UTC 53m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [us-east-1] Increased 5xx errors on write path major 2024-12-18 14:10 UTC 7h 4m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [europe-west4] Errors for some read and write path operations major 2024-12-17 15:19 UTC 18m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [europe-west4] Newly-created indexes failing to initialize minor 2024-12-17 14:47 UTC 3h 20m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [us-central1] High upsert latency for the 90 percentile minor 2024-12-17 07:20 UTC 37h 54m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [europe-west4] 504 and gRPC 14 errors for upsert operations major 2024-12-17 00:18 UTC 29m

Names an upstream provider: Google Cloud.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Multilingual e5 Large Query Availability none 2024-12-16 16:05 UTC 0m

  1. resolved

    From 10:37-10:54 multilingual e5 large embeddings were unavailable. The incident is now resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [us-east-1] 5xx errors for queries including values and/or metadata, queries by ID, and fetch operations critical 2024-12-10 18:21 UTC 46m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [us-west-2] Increase in 500 errors and latency for both read and write operations major 2024-12-05 09:48 UTC 14m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Control plane operations are failing for pod-based indexes to controller.pinecone.io major 2024-11-22 14:37 UTC 1h 32m

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [us-central1] Seeing an increase in internal errors for queries major 2024-11-21 16:21 UTC 6m

Names an upstream provider: Google Cloud.

  1. resolved

    The spike in internal errors was tied to a live deployment in this region and the impact subsided after approximately 5 minutes

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [us-east-1] Increased lag in freshness layer for some indexes minor 2024-11-21 13:06 UTC 3h 39m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [AWS] [us-east-1] Increase in internal errors (5xx) minor 2024-11-15 20:25 UTC 57m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless] [GCP] [us-central1] [europe-west4] Increase in internal errors (5xx) for Queries with filters major 2024-11-13 14:48 UTC 26m

Names an upstream provider: Google Cloud.

  1. resolved

    No more errors for the last 15 minutes. The fix has resolved the issue.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Increase in internal errors (5xx) for writes operations major 2024-11-12 15:37 UTC 4h 8m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

[Serverless][AWS][us-east-1] Increase in internal errors (500) for write operations minor 2024-11-05 15:10 UTC 4h 5m

Names an upstream provider: AWS.

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.

Serverless metrics in console not visible for time filters less than 12 hours minor 2024-10-31 20:34 UTC 21h 31m

  1. resolved

    This incident has been resolved.

Excerpts are shortened. Read the full incident on Pinecone's status page.