Upfirst - Notice history

OpenAI → Chat Completions API experiencing degraded performance

Web App - Operational

100% - uptime
Jul 2026
Aug 2026
Sep 2026

Real-Time Call Processor - Operational

100% - uptime
Jul 2026
Aug 2026
Sep 2026

Post-Call Processor - Operational

100% - uptime
Jul 2026
Aug 2026
Sep 2026

OpenAI → Realtime API - Operational

OpenAI → Chat Completions API - Degraded performance

Telnyx → Voice API - Operational

Telnyx → Outbound Messaging API - Operational

Telnyx → Number Searching API - Operational

Telnyx → Number Ordering API - Operational

ElevenLabs → Text to Speech API - Operational

Deepgram → Text to Speech API - Operational

Notice history

Sep 2026

Elevated errors for GPT-5.6 Sol on the API
  • Monitoring
    UTC
    Monitoring

    We have brought additional capacity online and are seeing improvements for some GPT-5.6 Sol API traffic.
    We continue to mitigate elevated errors affecting Chat Completions and Responses and are monitoring recovery

  • Identified
    UTC
    Identified

    We have identified that users are experiencing elevated errors for the impacted services.

    We are working on implementing a mitigation.

Web App is back up
  • Resolved
    UTC
    Resolved
    Web App is back up. This incident was automatically resolved by Instatus monitoring.
  • Update
    UTC
    Update

    Our engineering team is continuing to investigate. Calls are still being answered and we're working on getting the portal back up ASAP. Thank you for your patience.

  • Investigating
    UTC
    Investigating
    Web App is down at the moment. This incident was automatically created by Instatus monitoring.

Aug 2026

Elevated latency on Text-to-Speech and Speech-to-Text Requests
  • Resolved
    UTC
    Resolved

    The issue has been resolved. A root cause analysis will be shared shortly.

  • Monitoring
    UTC
    Monitoring

    Latency has returned to baseline levels.

Calls are slower to process than usual
  • Update
    UTC
    Update
    This incident has been resolved.
  • Resolved
    UTC
    Resolved

    Due to issues with Amazon Web Services, calls may be stuck processing longer than usual.

Elevated error rates on TTS, STT APIs
  • Resolved
    UTC
    Resolved

    The provider resolved the underlying issue at 07:13 UTC and error rates immediately returned to baseline.

  • Identified
    UTC
    Identified

    Between 06:39 and 07:13 UTC on August 3, a network issue at our upstream cloud provider caused elevated error rates and intermittent connection timeouts on Text-to-Speech and Speech-to-Text requests. At peak, approximately 2% of Speech-to-Text and 1% of Text-to-Speech requests were affected; retried requests generally succeeded. The provider resolved the underlying issue at 07:13 UTC and error rates immediately returned to baseline.

Jul 2026

Elevated error rates with the invalid_prompt error code
  • Resolved
    UTC
    Resolved

    All impacted services have now fully recovered.

  • Monitoring
    UTC
    Monitoring

    We have applied the mitigation and are monitoring the recovery.

  • Investigating
    UTC
    Investigating

    We are investigating the issue for the listed services.

[Deepgram API] Elevated Batch Error Rates: 400 error code responses
  • Resolved
    UTC
    Resolved

    This incident has been resolved.

  • Monitoring
    UTC
    Monitoring

    A fix has been implemented and traffic has returned to normal. We are monitoring the results.

  • Investigating
    UTC
    Investigating

    We are continuing to investigate an issue. STT batch requests may have returned 5xx errors, and some STT websockets may have experienced high latency, starting at 16:03 UTC.

  • Update
    UTC
    Update

    We are continuing to monitor for any further issues.

  • Monitoring
    UTC
    Monitoring

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

  • Update
    UTC
    Update

    We are continuing to investigate this issue.

  • Investigating
    UTC
    Investigating

    We are currently investigating an issue where some batch requests are returning 400 errors due to remote content download errors. Retrying the request one or more times often succeeds.

We’re seeing elevated latency, timeouts, and interrupted streaming across gpt 5.1 mini model and gpt 4.1 mini
  • Resolved
    UTC
    Resolved

    All impacted services have now fully recovered.

  • Investigating
    UTC
    Investigating

    We are investigating the issue for the listed services.

Elevated error rates
  • Resolved
    UTC
    Resolved

    All impacted services have now fully recovered.

  • Monitoring
    UTC
    Monitoring

    We have applied the mitigation and are monitoring the recovery.

  • Identified
    UTC
    Identified

    We have identified that users are experiencing elevated errors for the impacted services.

    We are working on implementing a mitigation.

Elevated error rates
  • Resolved
    UTC
    Resolved

    All impacted services have now fully recovered.

  • Monitoring
    UTC
    Monitoring

    We have applied the mitigation and are monitoring the recovery.

  • Investigating
    UTC
    Investigating

    We are investigating the issue for the listed services.

Jul 2026 to Sep 2026

Next