Cohere

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 claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Google Cloud.

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

1. investigating 2026-09-01 15:41 UTC

   🔎 We are currently investigating this live incident.

2. identified 2026-09-01 16:21 UTC

   🛠️ We have identified the root cause as an ongoing Google Cloud Platform (GCP) outage. Our team is actively monitoring the situation while we wait for GCP to resolve the underlying issue. ([reference](https://status.cloud.google.com/incidents/J5ia5t9p3g9Q5Wi7r8Ev "reference"))

3. monitoring 2026-09-01 19:47 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

4. resolved 2026-09-01 20:03 UTC

   🎉 The issue has been resolved and we are back to normal.

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

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 claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-08-05 19:36 UTC

   We are investigating a partial outage affecting our documentation site. Some documentation pages may not load correctly due to an ongoing issue with our upstream documentation provider (Fern). We are monitoring the incident and will share updates as they become available.

2. resolved 2026-08-05 20:33 UTC

   🎉 The issue has been resolved and we are back to normal.

3. resolved 2026-08-05 20:35 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: Login, tokens, certificates or credentials failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-07-23 22:56 UTC

   🔎 We are currently investigating an issue affecting the Cohere Dashboard ([dashboard.cohere.com](http://dashboard.cohere.com "dashboard.cohere.com")). Users may experience a continuous refresh loop on the login page, preventing successful authentication.

2. identified 2026-07-23 23:27 UTC

   🛠️ **Update:** We have identified the cause of login issues affecting the Cohere Dashboard, preventing successful logins. A fix is being implemented now and we expect Dashboard login to be restored shortly. **Note:** API access, model inference, and all other Cohere services are...

3. monitoring 2026-07-23 23:36 UTC

   👀 The issue affecting Dashboard login has been resolved ✅. We're monitoring to confirm stability. All Cohere services are operating normally.

4. resolved 2026-07-23 23:46 UTC

   🎉 The issue affecting Dashboard login has been resolved. All Cohere services are operating normally. Thank you for your patience while we worked through this.

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

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: A model or AI component. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2026-06-01 13:51 UTC

   /audio/transcriptions endpoints availability is affected now due to the Cohere ASR model backing the endpoint throws error for any audio inputs that are in the expected sampling rate. Previously these sampling rate audio files were accepted and processed, marking this as a...

2. resolved 2026-06-01 16:46 UTC

   🎉 The issue has been resolved and we are back to normal.

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

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 claude-haiku-5-5 with high confidence (taxonomy v0.2).

1. investigating 2026-04-20 22:16 UTC

   We are currently experiencing an outage affecting our documentation site due to an issue with our third-party documentation provider, Fern. Our team is actively monitoring the situation while the provider investigates and works on a fix.

2. resolved 2026-04-20 22:28 UTC

   Docs are back up!

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2026-04-13 19:36 UTC

   We are currently investigating Multiple Model Disruptions.

2. monitoring 2026-04-13 19:45 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

3. resolved 2026-04-13 21:00 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: A schema or data migration caused the failure. Root cause: A human mistake during operations. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. identified 2026-04-11 15:31 UTC

   There is a scheduled DB maintenance in progress. All the API authentication when accessing models are affected momentarily. The auth and API services is coming back online and should be fully up very soon.

2. resolved 2026-04-11 15:39 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: Network, DNS, routing or connectivity failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2026-02-13 04:34 UTC

   We are currently investigating an incident with chat models.

2. monitoring 2026-02-13 05:35 UTC

   We identified and resolved the connectivity problem affecting certain chat models. Affected models are starting to come back online.

3. resolved 2026-02-13 05:51 UTC

   The issue has been resolved and all models are back to normal operation

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

Failure mode: A configuration change caused the failure. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2025-10-18 21:46 UTC

   🛠️ We have identified the root cause of the incident, and are working diligently to fix.

2. resolved 2025-10-18 22:23 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: AI model returned degraded, wrong or empty output (not errors or timeouts). Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-10-01 15:56 UTC

   We have identified that the `logprobs` parameter is not working as expected for the following models: • `command-a-03-2025` • `command-a-reasoning-08-2025` The team is investigating the incident.

2. resolved 2025-10-01 19:46 UTC

   `logprobs` feature has been correctly marked as unavailable for the specified models.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. identified 2025-08-07 20:46 UTC

   🛠️ We have identified the root cause of the incident, and are working diligently to fix.

2. resolved 2025-08-07 20:56 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: Orchestration, control plane, service discovery or load balancing failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-07-25 15:54 UTC

   Command models are down due to a model serving infrastructure outage

2. investigating 2025-07-25 16:33 UTC

   🔎 We are currently investigating this live incident.

3. identified 2025-07-25 18:25 UTC

   🛠️ We have identified the root cause of the incident, and are working diligently to fix.

4. monitoring 2025-07-25 19:12 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

5. resolved 2025-07-25 19:52 UTC

   🎉 The issue has been resolved and we are back to normal.

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

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 claude-haiku-5-5 with high confidence (taxonomy v0.2).

Names an upstream provider: Google Cloud.

1. monitoring 2025-06-12 19:02 UTC

   We are currently experiencing an outage with Google Cloud Platform (GCP), which may impact some of our services. Our team is actively monitoring the situation.

2. resolved 2025-06-12 22:44 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-05-21 16:53 UTC

   🔎 We are currently investigating this live incident.

2. resolved 2025-05-21 19:15 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-05-08 14:25 UTC

   🔎 We are currently investigating this live incident.

2. monitoring 2025-05-08 17:14 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

3. resolved 2025-05-13 15:01 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-04-03 17:29 UTC

   🔎 We are currently investigating this live incident.

2. identified 2025-04-03 17:34 UTC

   🛠️ We have identified the root cause of the incident, and are working diligently to fix.

3. monitoring 2025-04-03 21:11 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

4. resolved 2025-04-04 20:58 UTC

   🎉 The issue has been resolved and we are back to normal.

5. resolved 2025-04-04 20:58 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: Exhausted memory, disk, CPU, queues, connection pools or quotas. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. monitoring 2025-04-02 22:20 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

2. resolved 2025-04-03 01:49 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-03-29 19:03 UTC

   🔎 We are currently investigating this live incident.

2. resolved 2025-03-29 19:14 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-03-28 20:40 UTC

   🔎 We are currently investigating this live incident.

2. resolved 2025-03-28 23:58 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-03-28 19:17 UTC

   🔎 We are currently investigating this live incident.

2. resolved 2025-03-28 19:38 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-03-27 17:51 UTC

   🔎 We are currently investigating this live incident.

2. resolved 2025-03-27 18:02 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. monitoring 2025-03-24 18:33 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

2. resolved 2025-03-24 20:26 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-03-20 18:00 UTC

   🔎 We are currently investigating this live incident.

2. resolved 2025-03-20 19:29 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: The text does not say enough to tell. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with low confidence (taxonomy v0.2).

1. investigating 2025-03-19 01:12 UTC

   🔎 We are currently investigating this live incident.

2. monitoring 2025-03-19 01:35 UTC

   👀 We are monitoring to make sure the incident has been fully resolved.

3. resolved 2025-03-19 11:46 UTC

   🎉 The issue has been resolved and we are back to normal.

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

Failure mode: Login, tokens, certificates or credentials failed. Root cause: The vendor does not say why it happened. Tagged by claude-haiku-5-5 with medium confidence (taxonomy v0.2).

1. investigating 2025-03-01 03:06 UTC

   🔎 We are currently investigating this live incident.

2. identified 2025-03-01 04:12 UTC

   🛠️ We have identified the root cause of the incident, and are working diligently to fix.

3. identified 2025-03-01 04:52 UTC

   🛠️ We have identified the root cause of the incident, and are working diligently to fix.

4. resolved 2025-03-01 05:51 UTC

   🎉 The issue has been resolved and we are back to normal.

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