Anthropic

From 17:30 UTC on Aug 25th to 02:00 UTC on Aug 28th, Claude Opus 4.1 experienced a degradation in quality for some requests. Users may have seen lower intelligence, malformed responses or issues with tool calling in Claude Code. This was caused by a rollout of our inference stack, which we have since rolled back for Claude Opus 4.1. While we often make changes intended to improve the efficienc...

From 17:30 UTC on Aug 25th to 02:00 UTC on Aug 28th, Claude Opus 4.1 experienced a degradation in quality for some requests. Users may have seen lower intelligence, malformed responses or issues with tool calling in Claude Code. This was caused by a rollout of our inference stack, which we have since rolled back for Claude Opus 4.1. While we often make changes intended to improve the efficienc...

We are investigating an issue with Claude Sonnet 4.0 that started at 22:30 PT / 5:30 UTC.

We are currently investigating this issue.

We are currently investigating this issue.

We have seen errors return to the baseline level since 5:05 PT / 13:05 UTC.

We are investigating an issue with Claude Opus 4.1 that started at 23:10 PT / 6:10 UTC.

We are investigating an issue with Claude Opus 4.1 similar to the one that happened earlier, this time starting with 4:14 PT / 11:14 UTC.

We are investigating an issue with Claude Opus 4.1 that started at 23:08 PT / 6:08 UTC.

We are currently investigating this issue.

Claude.ai is failing to downgrade MCP connections to SSE for a limited number of MCP servers. We are currently investigating.

We are currently investigating this issue.

We are currently investigating this issue.

Starting ~15:50 PT for Opus 4 and ~11:40 PT for Opus 4.1

The issue has been identified and a fix is being implemented.

We are currently investigating this issue.

We are currently investigating this issue.

The issue has been identified and a fix is being implemented.

We are currently investigating this issue.

We are currently investigating this issue.

The issue has been identified and a fix is being implemented.

We are investigating an elevated error rate on Claude Opus 4.1 that started since 6:22 PT / 13:22 UTC.

We have identified an issue that, since August 18, has caused Team plan organizations to be unable to add more members. We are working on a fix.

Starting August 15th, we have had problems with our upgrade flow. This was preventing upgraded accounts from getting their expected rate limit increases and expanded model access (Opus). We have identified the underlying issue and are working on a mitigation for impacted accounts.

Starting August 15th, we have had problems with our upgrade flow. This was preventing upgraded accounts from getting their expected rate limit increases and expanded model access (Opus). We have identified the underlying issue and are working on a mitigation for impacted accounts.

We are currently investigating this issue.

We are currently investigating this issue.

We are currently investigating this issue.

We are currently investigating an issue where we are seeing an elevated error rate across all models and products.

We are seeing an elevated amount of errors on Sonnet 3.6 since 22:30 PT / 6:30 UTC.

We're seeing a repeat of the incident that happened earlier today, with an increase of errors on Claude Sonnet 3.7 since 6:00 PT / 13:00 UTC.

Since 23:55 PT we have seen an increase of errors on the Claude Sonnet 3.7 model.

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

We are currently investigating elevated errors on requests to Claude 4 Sonnet on the API, Claude.ai, and the Anthropic Console.

We are currently investigating this issue.

This is a repeat of the previous incident. We've seen an increase in errors on Claude 4 Sonnet.

We are investigating an issue that started at around 6:15 PT / 13:15 UTC.