Serval - Notice history

Application - Operational

100% - uptime
Jul 2026 · 99.97%Aug · 99.53%Sep · 99.77%
Jul 2026
Aug 2026
Sep 2026

Workflows - Operational

Third Party: Anthropic → Claude API (api.anthropic.com) - Operational

Login - Operational

100% - uptime
Jul 2026 · 100.0%Aug · 100.0%Sep · 100.0%
Jul 2026
Aug 2026
Sep 2026

Notice history

View current status

Sep 2026

Elevated errors across ChatGPT, Codex, and the API including the Agents API
ResolvedDegraded performance5 hours 21 minutes
  • Resolved
    UTC
    Resolved

    The issue causing elevated errors across ChatGPT, Codex, and the API has been resolved, and all affected services have recovered.

    Thank you for your patience while we worked to restore service.

    The detailed Root Cause Analysis (RCA) will be published in the next 5 business days.

  • Update
    UTC
    Update

    We have applied the mitigation and are monitoring the recovery.

  • Update
    UTC
    Update

    We have applied the mitigation and are monitoring the recovery.

  • Update
    UTC
    Update

    We have applied the mitigation and are monitoring the recovery.

  • Monitoring
    UTC
    Monitoring

    We have applied the mitigation and are monitoring the recovery.

  • Update
    UTC
    Update

    We’re still investigating elevated errors affecting ChatGPT, Codex, and the API including the Agents API.

    Some users may experience failed requests, difficulty logging in or signing up, and tasks that do not complete. We’ll share updates as we learn more.

  • Investigating
    UTC
    Investigating

    We’re investigating elevated errors affecting ChatGPT, Codex, and the API including the Agents API.

    Some users may experience failed requests, difficulty logging in or signing up, and tasks that do not complete. We’ll share updates as we learn more.

  • Resolved
    UTC
    Resolved

SSO Login Issues
ResolvedMajor outage27 minutes
  • Resolved
    UTC
    Resolved

    This issue is resolved. WorkOS has recovered from their API errors.

  • Investigating
    UTC
    Investigating

    We are currently investigating issues with SSO-based login.

    It appears to be an issue with a downstream auth-provider, WorkOS.

    See https://status.workos.com/

Aug 2026

Third Party: OpenAI provider outage
ResolvedMajor outage9 hours 35 minutes
  • Resolved
    UTC
    Resolved

    We are continuing to use Anthropic for all agent responses as we monitor OpenAI's recovery. We will return to normal operation once API responsiveness returns to expected baseline.

  • Update
    UTC
    Update

    We are continuing to use Anthropic for all agent responses as we monitor OpenAI API incident response and recovery. Follow OpenAI's status updates here: https://status.openai.com/incidents/01M1CYZDD84XD0H56XNEV2PT98

  • Update
    UTC
    Update

    We are continuing to use Anthropic for all agent responses as we monitor OpenAI API recovery.

  • Update
    UTC
    Update

    We are continuing to observe issues with OpenAI API responsiveness, so will maintain failover to Anthropic models and continue monitoring.

  • Update
    UTC
    Update

    We are recording improved API responsiveness from OpenAI and are evaluating a progressive rollback to normal operations.

  • Update
    UTC
    Update

    We have completed failing remaining inference activity to Anthropic and are continuing to monitor OpenAI endpoints for recovery.

  • Update
    UTC
    Update

    We are continuing to failover to Anthropic and are implementing other mitigations.

  • Update
    UTC
    Update

    We are continuing to failover to Anthropic models for remaining affected agent behaviors and monitoring rollout.

  • Update
    UTC
    Update

    We are continuing to observe inconsistent response latencies with OpenAI endpoints. We are deploying a mitigation to failover all remaining affected model usages to Anthropic.

  • Monitoring
    UTC
    Monitoring

    We are seeing consistent availability from the OpenAI endpoint, but performance remains degraded. We are continuing to monitor the situation.

  • Update
    UTC
    Update

    We are continuing to see fluctuating availability and response times from OpenAI across multiple model classes. We are continuing to investigate and implement mitigations.

  • Update
    UTC
    Update

    We are currently investigating this issue with OpenAI. We are seeing some inconsistent response times from OpenAI.

  • Investigating
    UTC
    Investigating

    We are currently experiencing elevated error rates and API hangs communicating with OpenAI. We are investigating the issue.

Jul 2026

Previous

Jul 2026 to Sep 2026

Next