Deepgram: [Deepgram API] Elevated Batch Error Rates
Azure central us outage, Jul 18, 2024 · 9 vendors, 9 incidents
Deepgram’s incident started in the same window without naming Azure (timing only, not evidence of a link). (timing only, posted +6 min vs the first vendor naming Azure)
Swipe sideways to see the whole diagram.
Mermaid source
flowchart LR
root["Azure central us<br/>own incident not archived"]:::inferred
h1["Within an hour<br/>5 vendors, 1 blamed Azure<br/>MongoDB Atlas, Confluent, GitHub, GitHub Copilot +1"]:::blames
root --> h1
later["Later<br/>1 vendor<br/>Contentstack"]:::names
root --> later
me["Deepgram (this incident)<br/>posted +6 min"]:::me
root -.->|"same window"| meFull event: timeline, evidence and all vendors →
Detected automatically from incidents that started together and named the same provider. A link means one vendor’s incident named another, not a confirmed cause.
Timeline of updates
- resolved
This incident is resolved. All systems are operational.
From Deepgram’s published incident history: for incidents before Rewindex began polling this status page, only the final update text is available.
Archive proof
Rewindex commits each version of an incident it captures to a daily checkpoint, chains it to the day before, and has the checkpoint timestamped by FreeTSA and DigiCert.
How the archive is checked, and what it cannot prove.
This incident predates live tracking (October 17, 2026). It came from the vendor’s own published history, which is not covered by checkpoints.
Impact, status and times are the vendor’s own, as last archived. View on status.deepgram.com (opens in new tab).