AI APIs / LLM API / Anthropic API

Anthropic API

OPERATIONAL

Since Jul 2026 · 50 incidents · status.claude.com · checked just now

CompareStatus page
GradeDLast 90 days
DPRODBSHIP

Overview

30d90d1y
Admitted uptimeTime not covered by a Sev 1 the provider posted itself. A best case.
99.993%Grade D
IncidentsEverything posted on the status page except scheduled maintenance.
501 Sev 1
Sev 1 downtimeTotal minutes of Sev 1 incidents, as posted.
36m
Median fixMedian time to resolve. Half of incidents were fixed faster.
1h 13m
LongestLongest single incident, start to resolved.
6d 4h
Since lastTime since the last counted incident was resolved.
12h 34m

By area

DProduction
38INCIDENTS
2d 14hAFFECTED
Your users are hit: apps, APIs, databases, inference
Worst, 1y
SEV 1Aug 16, 2026 · 36mService disruption on Claude services
SEV 2Aug 5, 2026 · 7h 09mDegraded performance of multiple models
SEV 2Oct 1, 2026 · 6h 16mDelayed credits on the Claude Platform
Most hit
Claude API (api.anthropic.com)33
Claude Code32
Claude Cowork32
claude.ai31
Worse. 38 in the last 6 months, 0 in the 6 before.
BShipping
12INCIDENTS
18h 09mAFFECTED
You can't deploy, build or manage: CI, CLI, dashboard, auth, billing
Worst, 1y
SEV 1Aug 16, 2026 · 36mService disruption on Claude services
SEV 3Oct 1, 2026 · 6h 16mDelayed credits on the Claude Platform
SEV 3Aug 28, 2026 · 2h 59mElevated errors on Claude Code and Claude Cowork
Most hit
Claude Code7
Claude Cowork7
claude.ai6
Claude API (api.anthropic.com)5
Worse. 12 in the last 6 months, 0 in the 6 before.
CleanSev 3–4Sev 1–2No data

Trend, last 12 months

Worse. 50 in the last 6 months, 0 in the 6 before.

Severity mix

Sev 1 · Lights outProd site, API or database down, or data loss1
Sev 2 · BleedingProd degraded or partly down33
Sev 3 · Can't shipCan't deploy, build or manage it7
Sev 4 · PapercutDocs, status page, slow dashboard9

When it breaks

Start times, last 12 months, UTC.

What breaks

claude.ai38 incidents
Claude Cowork35 incidents
Claude Code34 incidents
Claude API (api.anthropic.com)33 incidents
Claude Console (platform.claude.com)10 incidents

Communication

Updates eachStatus page updates per incident, on average.
3.2Last 12 months
Update gapMedian time between status page updates during an incident.
29mLast 12 months
PostmortemsSev 1–2 incidents with a published write-up.
0 of 34Sev 1–2

Incident history

Show all 50
Oct 22, 20264h 17mSEV 4
Elevated errors affecting ConnectorsConnectors errors hit claude.ai and Claude Cowork for about four hours; the text does not give the share of users affected.AI-graded · claude.ai +1
Why this grade
  1. RULES · SEV 4
    Sev 4 because claude.ai had degraded performance
  2. CLAUDE · SEV 4 · UNCLEAR · MEDIUM CONFIDENCE
    Connectors errors hit claude.ai and Claude Cowork for about four hours; the text does not give the share of users affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
  1. 03:50 UTC · investigating
    We are investigating elevated errors affecting connectors. We will provide an update as soon as possible.
  2. 07:28 UTC · monitoring
    A fix has been deployed for the issue affecting claude.ai and Claude Cowork and we are monitoring for recovery.
  3. 08:07 UTC · resolved
    The issue affecting claude.ai and Claude Cowork has been resolved.
Source
Oct 21, 202640mSEV 2
Degraded performance for Claude Fable 5Elevated errors on requests to Claude Fable 5 for about 40 minutes; the text does not give the share of requests failing.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 2
    Sev 2 because Claude API (api.anthropic.com) had degraded performance
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors on requests to Claude Fable 5 for about 40 minutes; the text does not give the share of requests failing.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 19:49 UTC · investigating
    We are investigating elevated errors on requests to Claude Fable 5. We will provide an update as soon as possible.
  2. 20:29 UTC · resolved
    The issue affecting other Claude models has been resolved.
Source
Oct 7, 20260mSEV 2
Issue with spend limitsSome organizations were wrongly paused for reaching spend limits, so their API requests were refused; the rest were unaffected.AI-graded · some customers
Why this grade
  1. RULES · SEV 1
    Sev 2 from the incident title (no components listed), raised to Sev 1 for security
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Some organizations were wrongly paused for reaching spend limits, so their API requests were refused; the rest were unaffected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
1 update
  1. 21:23 UTC · resolved
    We have identified an issue which resulted in some organizations to be incorrectly paused for having reached their spend limit, resulting in refused requests on the Claude API, Claude.ai, Claude Code, Claude Security, and Claude Cowork. This is now resolved.
Source
Oct 7, 20266d 4hSEV 4
Elevated errors on platform.claude.comElevated errors loaded usage data on the Claude Console Usage and Rate limits pages and in the Admin API usage report from October 7 to October 13. Core functionality and API requests were not affected. Recent usage was delayed about 30 minutes after mitigation while a full fix was prepared. Resolved October 13.AI-graded · Claude Console (platform.claude.com)
Why this grade
  1. RULES · SEV 3
    Sev 3 because Claude Console (platform.claude.com) had a partial outage
  2. CLAUDE · SEV 4 · GLOBAL · HIGH CONFIDENCE
    Usage and rate limit pages in the Claude Console and the Admin API usage report failed to load for several days; API requests were not affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
5 updates
  1. 13:25 UTC · investigating
    We are investigating elevated errors affecting usage data on the platform.claude.com Usage page and the Admin API usage report. Core functionality is not affected. We will provide an update as soon as possible.
  2. 16:36 UTC · investigating
    We are continuing to work on elevated errors affecting usage data on the platform.claude.com Usage and Rate limits pages and the Admin API usage report. A mitigation for the Usage page and the Admin API usage report is rolling out; once it is in place, the most recent usage may take about 30 minutes to appear there. Core functionality is not affected.
  3. 17:28 UTC · identified
    We've identified the cause of errors loading usage data. The Admin API usage report has recovered, and fixes for the platform.claude.com Usage and Rate limits pages are in progress. The most recent 30 minutes of usage may be delayed. Core functionality is not affected.
  4. 21:44 UTC · monitoring
    We've mitigated the errors loading usage data on platform.claude.com and in the Admin API usage report. While we work on a full fix, the most recent ~30 minutes of usage may take longer to appear on the platform.claude.com. API requests are not affected, and we will provide additional updates here.
  5. 18:00 UTC · resolved
    This issue has been resolved.
Source
Oct 7, 20261h 13mSEV 3
Elevated errors loading usage data on platform.claude.comUsage page and Admin API usage report returned errors for about 100 minutes; Messages API was not affected.AI-graded · Claude Console (platform.claude.com)
Why this grade
  1. RULES · SEV 3
    Sev 3 because Claude Console (platform.claude.com) had a partial outage
  2. CLAUDE · SEV 3 · UNCLEAR · MEDIUM CONFIDENCE
    Usage page and Admin API usage report returned errors for about 100 minutes; Messages API was not affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 01:20 UTC · investigating
    We are investigating elevated errors loading usage data on the platform.claude.com Usage page and the Admin API usage report endpoint since 5 PM PT. Messages API requests are not affected. We will provide an update as soon as possible.
  2. 02:33 UTC · resolved
    This incident has been resolved. From 17:00 PT on October 6 / 00:00 UTC on October 7 to 18:40 PT on October 6 / 01:40 UTC on October 7, many requests to load usage data on the platform.claude.com Usage page and the Admin API usage report returned errors.
Source
Oct 6, 202619mSEV 2
Elevated errors for Claude Opus 5.5Elevated errors on requests to Claude Opus 5.5 for about 19 minutes; the text does not say other models were affected.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors on requests to Claude Opus 5.5 for about 19 minutes; the text does not say other models were affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
  1. 12:24 UTC · investigating
    We are investigating elevated errors on requests to Claude Opus 5.5. We will provide an update as soon as possible.
  2. 12:37 UTC · identified
    We have identified the cause of elevated errors on requests to Claude Opus 5.5 and are working on a fix. We will provide an update as soon as possible.
  3. 12:43 UTC · resolved
    The issue affecting Claude Opus 5.5 has been resolved.
Source
Oct 5, 202616mSEV 2
Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1Elevated errors on requests to two Claude models for about 30 minutes; other models were not described as affected.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors on requests to two Claude models for about 30 minutes; other models were not described as affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 13:05 UTC · investigating
    We are investigating elevated errors on requests to Claude Mythos 5.1 and Claude Fable 5.1. We will provide an update as soon as possible.
  2. 13:21 UTC · resolved
    The issue affecting Claude Mythos 5.1 and Claude Fable 5.1 has been resolved. Impact occurred from 05:40 PT / 12:40 UTC to 06:10 PT / 13:10 UTC.
Source
Oct 1, 20266h 16mSEV 2
Delayed credits on the Claude PlatformCredit purchases were delayed in reflecting on balances, so some API requests failed for insufficient credit; scope not stated.AI-graded · Claude Console (platform.claude.com) +1
Why this grade
  1. RULES · SEV 2
    Sev 2 because Claude API (api.anthropic.com) had degraded performance
  2. CLAUDE · SEV 2 · UNCLEAR · MEDIUM CONFIDENCE
    Credit purchases were delayed in reflecting on balances, so some API requests failed for insufficient credit; scope not stated.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
  1. 16:20 UTC · investigating
    We are investigating delays in credit purchases being reflected in account balances, resulting in some requests failing for insufficient credit balance. We will provide an additional update as soon as possible.
  2. 18:23 UTC · monitoring
    We have resolved the issue causing delays in credits being applied after purchase. We are monitoring closely to ensure no further issues.
  3. 22:36 UTC · resolved
    This issue has been resolved.
Source
Sep 29, 20262h 06mSEV 2
Elevated errors on claude.ai, Claude Code, Claude Cowork and the Claude APIFrom 14:00 to 14:59 UTC, Claude API requests returned elevated errors and Claude Code, Cowork, sign-in, SSO, purchases and file uploads failed for many users. A mitigation cut error rates by 14:36, and services were restored by 14:59 UTC. Some messages sent in that window may not have been saved.AI-graded · claude.ai +4
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · GLOBAL · HIGH CONFIDENCE
    Claude API errors and Claude Code, Cowork and sign-in failures lasted about 60 minutes across services, with most recovered by 14:59 UTC.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
8 updates
  1. 14:21 UTC · investigating
    We are investigating elevated error rates affecting Claude.ai (including the desktop and mobile apps), Claude Code and Claude Cowork. Users may see failed requests, errors loading or sending conversations, or be asked to sign in again; retrying may succeed. We will provide an update as soon as possible.
  2. 14:28 UTC · investigating
    We are investigating elevated error rates affecting Claude.ai (including the desktop and mobile apps), Claude Code and Claude Cowork. Some requests to the Claude API are also returning errors. We will provide an update as soon as possible.
  3. 14:30 UTC · investigating
    We are investigating reports of degraded performance affecting claude.ai, platform.claude.com, the Claude API, Claude Code, and Claude Cowork. We will provide an update as soon as possible.
  4. 14:41 UTC · investigating
    We have applied a mitigation and error rates have dropped substantially. Some sign-in attempts, account actions and Claude Code and Cowork sessions are still failing. We are continuing to work on a full fix.
  5. 15:00 UTC · investigating
    The errors that began at 14:00 UTC were mitigated at 14:36 UTC, and existing conversations are mostly working again. A second issue is preventing many users from signing in (single sign-on and Sign in with Apple are unavailable), starting new chats, voice conversations and Claude Code or Cowork sessions, making purchases, and uploading files. If you're signed in, please don't sign out. We're working on a fix and will post another update within 30 minutes.
  6. 15:11 UTC · monitoring
    Most services have recovered as of 14:59 UTC. Signing in, starting new chats, voice conversations, Claude Code and Cowork sessions, purchases and file uploads are working again. Some messages sent between 14:00 and 14:59 UTC may not have been saved. We are monitoring closely and will post another update within 30 minutes.
  7. 15:30 UTC · monitoring
    All services have been operating normally since 14:59 UTC. We are continuing to monitor.
  8. 16:27 UTC · resolved
    The issue affecting Claude.ai, the Claude desktop and mobile apps, Claude Code, Claude Cowork, and the Claude API has been resolved, and services have been operating normally since recovery. Impact occurred from 07:00 PT / 14:00 UTC to 07:59 PT / 14:59 UTC.
Source
Sep 22, 20261h 38mSEV 2
Elevated errors for multiple modelsRequests to several named Claude models (Mythos 5 and 5.1, Fable 5 and 5.1, Opus 5) returned elevated errors from about 00:50 to 02:10 UTC. Success rates recovered after a fix; the provider did not describe the cause in detail. Claude.ai, the API, Claude Code and Cowork were listed as affected components.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors hit requests to specific Claude models (Mythos 5/5.1, Fable 5/5.1, Opus 5) for about 75 minutes; other models were not named as affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
5 updates
  1. 00:57 UTC · investigating
    We are investigating elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5. We will provide an update as soon as possible.
  2. 01:17 UTC · identified
    We have identified the cause of elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 and are working on a fix. We will provide an update as soon as possible.
  3. 01:35 UTC · identified
    We are continuing to work to resolve errors affecting some models. At this time, requests to Claude Fable 5 and 5.1 and Mythos 5 and 5.1 have returned to normal success rates. We are working to resolve remaining errors affecting Claude Opus 5, and will provide an additional update shortly.
  4. 02:11 UTC · monitoring
    We have seen success rates return to normal across affected models, and are monitoring closely to ensure no further issues.
  5. 02:35 UTC · resolved
    This issue has been resolved. Impact occurred from 5:50pm PT / 00:50 UTC to 7:10pm PT / 02:10 UTC.
Source
Sep 16, 202633mSEV 3
Issues with Google Play subscriptionsUsers could not create or manage Anthropic subscriptions purchased through Google Play for about 33 minutes; API serving was not mentioned.AI-graded · some customers
Why this grade
  1. RULES · SEV 4
    Sev 4 from the incident title (no components listed)
  2. CLAUDE · SEV 3 · SUBSET · LOW CONFIDENCE
    Users could not create or manage Anthropic subscriptions purchased through Google Play for about 33 minutes; API serving was not mentioned.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 16:18 UTC · identified
    We are aware of an issue affecting users interacting with subscriptions via Google Play, such as when creating a new subscription on Android devices. Google has confirmed an issue with Google Play, and we are awaiting their further updates.
  2. 16:51 UTC · resolved
    This issue has been resolved.
Source
Sep 15, 20261h 26mSEV 2
Intermittent error spikes for Claude Mythos 5.1 and Claude Fable 5.1Anthropic saw elevated errors on requests to Claude Mythos 5.1 and Claude Fable 5.1 from about 09:48 to 11:14 UTC on September 15. A fix was deployed around 10:50 and monitored until resolution. The text does not describe the cause in detail.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Intermittent elevated errors on two specific Claude models for about 85 minutes; other models were not reported affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
4 updates
  1. 09:48 UTC · investigating
    We are investigating elevated errors on requests to Claude Mythos 5.1 and Claude Fable 5.1. We will provide an update as soon as possible.
  2. 09:52 UTC · investigating
    We are investigating elevated errors on requests to Claude Mythos 5.1 and Claude Fable 5.1. We will provide an update as soon as possible.
  3. 10:50 UTC · monitoring
    A fix has been deployed for Claude Mythos 5.1 and Claude Fable 5.1 and we are monitoring to ensure it has resolved the issue.
  4. 11:14 UTC · resolved
    A fix has been deployed for Claude Mythos 5.1 and Claude Fable 5.1 and we are monitoring to ensure it has resolved the issue.
Source
Sep 11, 202617mSEV 2
Elevated errors for Claude Mythos 5.1 and Claude Fable 5.1Requests to Claude Mythos 5.1 and Claude Fable 5.1 saw elevated errors from about 13:57 to 14:20 UTC on September 11, 2026. The provider deployed a fix and resolved the incident at 14:37 UTC. The cause was not detailed in the update text. Claude.ai, Claude Code and Cowork were listed as affected components.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors hit requests to two specific Claude models for about 23 minutes; other models were not described as affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
5 updates
  1. 14:19 UTC · investigating
    We are investigating elevated errors on requests to Claude Fable 5.1 and Claude Mythos 5.1. We will provide an update as soon as possible.
  2. 14:21 UTC · identified
    We have identified the cause of elevated errors on requests to Claude Mythos 5.1 and Claude Fable 5.1 and are working on a fix. We will provide an update as soon as possible.
  3. 14:28 UTC · monitoring
    A fix has been deployed for Claude Mythos 5.1 and Claude Fable 5.1 and we are monitoring for recovery.
  4. 14:28 UTC · monitoring
    A fix has been deployed for the issue affecting Claude services and we are monitoring for recovery.
  5. 14:37 UTC · resolved
    The issue affecting Claude services has been resolved. Impact occurred from 13:57 to 14:20 UTC
Source
Sep 10, 20261h 41mSEV 2
Elevated latency on the Claude API for some usersClaude API requests were slow and some timed out for customers routed through the US Midwest for about 100 minutes.AI-graded · regional · Claude API (api.anthropic.com) +1
Why this grade
  1. RULES · SEV 2
    Sev 2 because Claude API (api.anthropic.com) had degraded performance
  2. CLAUDE · SEV 2 · REGIONAL · MEDIUM CONFIDENCE
    Claude API requests were slow and some timed out for customers routed through the US Midwest for about 100 minutes.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 21:43 UTC · identified
    We are experiencing slower than normal response times on the Claude API for some customers whose traffic enters through the US Midwest. Users may experience elevated latency and some request timeouts.
  2. 23:24 UTC · resolved
    The issue affecting Claude services has been mitigated.
Source
Sep 10, 20264d 3hSEV 4
Degraded functionality for Claude Cowork on WindowsAfter a September 8 Windows update, Claude Cowork on Windows could not run local commands because its workspace lost access to the computer's drive. Chat and file reading and editing still worked for most users. Restarting or reinstalling did not help. Microsoft released a September 14 Windows update that fixed the issue, and the incident was resolved that day.AI-graded · some customers · Claude Cowork
Why this grade
  1. RULES · SEV 1
    Sev 1 from the incident title (no components listed)
  2. CLAUDE · SEV 4 · SUBSET · MEDIUM CONFIDENCE
    Claude Cowork on Windows could not run local commands after a Windows update for about four days; chat and file reading still worked.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 15:54 UTC · identified
    A Windows update released September 8 has left Claude Cowork on Windows unable to run local commands, because its workspace can no longer reach your computer's drive. For most users, chat and file reading and editing still work. There's no in-app workaround yet, and restarting or reinstalling won't help. Microsoft has developed a fix and is working to release it. We'll post an update when we have more to share.
  2. 19:14 UTC · resolved
    This issue has been resolved. Microsoft has released a September 14 Windows update that fixes it: https://support.microsoft.com/en-us/servicing/os/windows-11/2026/09/kb5129195-windows-11-24h2-25h2-security-update
Source
Sep 3, 20262h 57mSEV 2
Elevated errors for multiple modelsElevated errors affected requests to multiple Claude models, including Mythos, Fable and Opus versions, from about 13:26 to 16:16 UTC on September 3. Opus 4.8 and Opus 5 were the last affected. A fix was deployed for Mythos 5.1, Fable 5.1 and Opus 5, and the incident was resolved. Claude.ai, Claude Code and Cowork were listed as affected components.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors hit requests to several Claude models for about three hours; other models and most customers were largely unaffected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
7 updates
  1. 13:26 UTC · investigating
    We are investigating elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5. We will provide an update as soon as possible.
  2. 13:41 UTC · identified
    We have identified the cause of elevated errors on requests to Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 and are working on a fix. We will provide an update as soon as possible.
  3. 13:50 UTC · identified
    An exhaustive list of affected models: Mythos/Fable 5.1, Mythos/Fable 5, Opus 5, Opus 4.8, Opus 4.6.
  4. 14:49 UTC · identified
    We are continuing to work on a fix for this issue.
  5. 15:25 UTC · identified
    The only affected models right now are Opus 4.8 and Opus 5. The rest of the models have recovered to baseline error rate.
  6. 16:06 UTC · monitoring
    A fix has been deployed for Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 and we are monitoring for recovery.
  7. 16:23 UTC · resolved
    The issue affecting Claude Mythos 5.1, Claude Fable 5.1, and Claude Opus 5 has been resolved. Impact has ended as of 9:16 PT / 16:16 UTC.
Source
Sep 3, 202619mSEV 2
Elevated errors for Claude Sonnet 5Elevated errors on requests to Claude Sonnet 5 for about 19 minutes; the text does not give failure rates or other models' status.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors on requests to Claude Sonnet 5 for about 19 minutes; the text does not give failure rates or other models' status.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
  1. 12:37 UTC · investigating
    We are investigating elevated errors on requests to Claude Sonnet 5. We will provide an update as soon as possible.
  2. 12:47 UTC · monitoring
    A fix has been implemented and we are monitoring the results.
  3. 12:56 UTC · resolved
    This incident has been resolved.
Source
Sep 2, 202626mSEV 2
Elevated errors for Claude Sonnet 5Elevated errors on requests to one model, Claude Sonnet 5, lasted about 15 minutes; other models were not reported affected.AI-graded · some customers · claude.ai +3
Why this grade
  1. RULES · SEV 1
    Sev 1 because Claude API (api.anthropic.com) had a partial outage
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Elevated errors on requests to one model, Claude Sonnet 5, lasted about 15 minutes; other models were not reported affected.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 21:17 UTC · investigating
    We are investigating elevated errors on requests to Claude Sonnet 5. We will provide an update as soon as possible.
  2. 21:44 UTC · resolved
    The issue affecting Claude Sonnet 5 has been resolved. Impact occurred from 2:05pm PT / 21:05 UTC to 2:19pm PT / 21:19 UTC.
Source
Sep 1, 20261h 58mSEV 2
Delays in credit purchasesSome API requests failed with 'credit balance too low' errors for users who had hit zero credits; newly purchased credits were delayed.AI-graded · some customers · Claude Console (platform.claude.com)
Why this grade
  1. RULES · SEV 4
    Sev 4 because Claude Console (platform.claude.com) had degraded performance
  2. CLAUDE · SEV 2 · SUBSET · MEDIUM CONFIDENCE
    Some API requests failed with 'credit balance too low' errors for users who had hit zero credits; newly purchased credits were delayed.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
2 updates
  1. 23:26 UTC · monitoring
    We have identified and resolved an issue where users who reached a balance of zero usage credits saw delays in the availability of newly purchased credits, resulting in some requests to the Claude API receiving 'credit balance is too low' errors erroneously. This affected credits purchased from 05:10am PT / 12:10 UTC to 2:35pm PT / 21:35 UTC. At this time, newly purchased credits should be available as expected and we are working to resolve any remaining impact.
  2. 01:24 UTC · resolved
    This issue has been resolved.
Source
Sep 1, 20261h 02mSEV 4
Degraded performance on platform.claude.com and Claude for Microsoft Office 365Degraded performance on the Claude Console and claude.ai for about an hour; core inference and the API were not impacted.AI-graded · claude.ai +1
Why this grade
  1. RULES · SEV 4
    Sev 4 because claude.ai had degraded performance
  2. CLAUDE · SEV 4 · UNCLEAR · MEDIUM CONFIDENCE
    Degraded performance on the Claude Console and claude.ai for about an hour; core inference and the API were not impacted.
  3. Claude Haiku 5.5 · prompt v5 · Oct 22, 2026 · Raw record
3 updates
  1. 17:05 UTC · investigating
    We are investigating reports of degraded performance affecting some Claude services, including docs.claude.com. We are working to resolve these issues and will provide an update as soon as possible.
  2. 17:52 UTC · monitoring
    We are seeing success rates recover across affected services. Core inference and the API are not impacted.
  3. 18:07 UTC · resolved
    This issue has been resolved.
Source

Peers, 90 days

Compare
GroqGrade B100.00% up3 incidentsMTTR 23mCohereGrade C100.00% up2 incidentsMTTR 4h 22mOpenAI APIGrade C100.00% up27 incidentsMTTR 1h 38mAnthropic APIGrade D99.97% up50 incidentsMTTR 1h 13m

README badge

Anthropic API's live grade, for your README.

Anthropic API grade badge
[![anthropic on downagain.dev](https://downagain.dev/badge/anthropic.svg)](https://downagain.dev/p/anthropic)