Unverified50% confidenceEventExact time
Incident timeline: a large number of error reports was first confirmed at 14:21 UTC; it expanded to the Claude API at 14:28 UTC; mitigation measures were implemented at 14:36 UTC and the error rate dropped significantly; most services recovered at 14:59 UTC but a second independent issue was exposed (SSO and Apple login unavailable); and at 16:27 UTC all issues were announced as resolved.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedThe Anthropic status page made two updates for this incident: at 01:20 UTC it confirmed the high-frequency errors, and at 02:33 UTC it issued a resolved notice.72% similarUnverifiedTwenty minutes after the first report, the team updated the status to 'Identified'; at UTC 01:35 some models (Claude Fable 5 and 5.1, Mythos 5 and 5.1) recovered, at UTC 02:11 all affected models returned to normal and entered monitoring, and at UTC 02:35 the status was marked as 'Resolved.'61% similarUnverifiedThis update fixes an issue where the gateway OTLP telemetry relay would pause all forwarding for 30 seconds after rejecting malformed or oversized payloads.58% similarUnverifiedThis version fixes an issue where excessively large failure output from background tasks caused API request bodies to exceed size limits and fail57% similarUnverifiedv0.23.0 redacts exception details from default tool failure details, streaming task exception stack traces, and Realtime tool error events.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1008465API
curl https://kongchang.com/api/v1/knowledge/claims/1008465MCP
get_claim(id=1008465)