Is Claude Down?
Anthropic · API & platform status
Claude 4, Claude 3.5, Claude API, Claude Code, and all Anthropic platform services.
Official status data last reflected here:
[ STATUS AT A GLANCE ]
System Components
Current status of individual Anthropic services
Anthropic down? Route around it.
When Anthropic has issues, Bifrost automatically routes your requests to a healthy alternative provider. Zero code changes. 99.999% effective uptime.
About Anthropic
What Anthropic does, where the data on this page comes from, and recent reliability
[ ABOUT ANTHROPIC ]
About Anthropic
Anthropic provides Claude, Claude API, Claude Code, and Claude Sonnet. Anthropic outages often matter most to engineering, agent, and internal tooling use cases where Claude is deeply embedded into day-to-day developer workflows.
This page pulls data from Anthropic's official status page to show current service health, any active incidents, and a history of recent issues, all in one view.
[ DATA SOURCES ]
Full incident history available
Anthropic publishes detailed component status, a full incident archive, and scheduled maintenance data through their official status page.
- Data pulled from Anthropic's official status page (status.claude.com)
- Refreshed every 60 seconds
- Covers Claude, Claude API, Claude Code, Claude Sonnet, and Claude Opus
- Includes full incident archive and scheduled maintenance history
[ RELIABILITY ]
Recent reliability
- 50 incidents reported over the last 90 days.
- The most recent incident was reported today.
- All 6 monitored components are currently operational.
- Most frequently affected: Claude Code, claude.ai, and Claude API (api.anthropic.com).
[ COMMON USE CASES ]
How teams use Anthropic
Anthropic outages often matter most to engineering, agent, and internal tooling use cases where Claude is deeply embedded into day-to-day developer workflows.
Incidents & Maintenance
Active incidents, scheduled maintenance, and incident history for Anthropic
Past Incidents
Elevated errors across many models
Aug 4, 2026 · Resolved Aug 4, 2026
This issue has been resolved.
We have identified an issue which resulted in some users experiencing issues when attempting to log into Anthropic services, including Claude.ai and Claude Code via oAuth. Additionally, some users saw errors when making requests to models. At this time, we have seen success rates recover and are monitoring closely to ensure there are no further issues.
We are currently investigating this issue.
Elevated errors on Claude Sonnet 5
Aug 4, 2026 · Resolved Aug 4, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Elevated errors on Claude Sonnet 5
Aug 4, 2026 · Resolved Aug 4, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Degraded performance on Claude Sonnet 5
Aug 3, 2026 · Resolved Aug 3, 2026
As of 15:20 UTC (8:20am PT), error rates on Claude Sonnet 5 have returned to baseline. This incident is resolved.
We are currently investigating this issue.
Error rates across multiple models
Aug 3, 2026 · Resolved Aug 3, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Degraded performance on Claude Sonnet 5
Jul 31, 2026 · Resolved Jul 31, 2026
This incident has been resolved.
We are currently investigating this issue.
Degraded performance on Claude Opus 4.8
Jul 30, 2026 · Resolved Jul 30, 2026
This incident has been resolved.
We are currently investigating this issue.
Elevated errors across many models
Jul 30, 2026 · Resolved Jul 30, 2026
This incident has been resolved.
We are also investigating issues with Opus 4.7 and Opus 4.5.
As of 2:58 PT / 9:58 UTC the errors are back to baseline.
As of 01:33 PT / 08:33 UTC we are back to errors across all models.
As of 8:05 UTC / 1:05 PT, Sonnet 5 errors are back to baseline, but we're seeing an increased error rate on Fable 5.
+ 3 more updates
Elevated errors across all models
Jul 29, 2026 · Resolved Jul 29, 2026
This issue has been resolved.
From 12:45 PT / 19:45 UTC through to 1:26 PT / 21:26 UTC, we saw elevated rates of errors across Claude models. We have seen recovery in success rates across all models and are monitoring closely to ensure no further issues.
We are continuing to work to fully resolve issues resulting in elevated requests and latency to Claude models. At this time, we are seeing recovery across most models. We will provide an additional update as soon as possible.
We have identified an issue resulting in elevated errors across multiple models, and are working to resolve this. We will provide an update as soon as possible.
We are currently investigating this issue.
Elevated errors on Claude Opus 5 and Haiku 4.5
Jul 27, 2026 · Resolved Jul 27, 2026
As of 7:34 PST / 14:34 UTC the errors have returned to baseline.
Haiku 4.5 is also returning errors.
We are currently investigating this issue.
We are continuing to investigate this issue.
We are currently investigating this issue.
Elevated errors on Claude Opus 5
Jul 27, 2026 · Resolved Jul 27, 2026
As of 4:47 PST / 11:47 UTC the errors have returned to baseline.
We are currently investigating this issue.
Elevated errors on Claude Opus 5
Jul 27, 2026 · Resolved Jul 27, 2026
As of 2:03 PST / 9:03 UTC the errors have returned to baseline.
We are currently investigating this issue.
Elevated errors for Opus 5
Jul 26, 2026 · Resolved Jul 26, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
We are continuing to work on a fix for this issue.
The issue has been identified and a fix is being implemented.
We are currently investigating this issue.
Elevated errors for Claude Fable 5, Claude Sonnet 5, Claude Haiku 4.5, and other models
Jul 25, 2026 · Resolved Jul 25, 2026
This incident has been resolved.
We are investigating elevated errors on requests to Claude Fable 5, Claude Sonnet 5, Claude Haiku 4.5, and other Claude models. We will provide an update as soon as possible.
Elevated errors for Mythos 5, Fable 5, Opus 5 and Claude Haiku 4.5
Jul 25, 2026 · Resolved Jul 25, 2026
This incident has been resolved.
The issue has been identified and a fix is being implemented.
We are investigating elevated errors on requests to Claude Mythos 5, Claude Fable 5, and Claude Haiku 4.5. We will provide an update as soon as possible.
Sonnet 4.6 and Sonnet 5 errors elevated
Jul 25, 2026 · Resolved Jul 25, 2026
For approximately 10 minutes, error rates on Sonnet 4.6 and 5 were elevated. Service returned to normal at approximately 11:07a PDT.
Microsoft Office add-in availability
Jul 22, 2026 · Resolved Jul 24, 2026
This issue has been resolved.
Users who installed the following add-ins may experience issues accessing the add-in functionality: Claude by Anthropic for PowerPoint, Claude by Anthropic for Word, and Claude by Anthropic for Excel. To regain immediate access to Claude for Microsoft 365, install the add-in here: https://marketplace.microsoft.com/en-us/product/office/wa200010725
Elevated error rate on Opus 4.8
Jul 24, 2026 · Resolved Jul 24, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Elevated errors on Haiku 4.5
Jul 22, 2026 · Resolved Jul 23, 2026
This incident has been resolved.
We are currently investigating this issue.
Service disruption on Claude Services
Jul 22, 2026 · Resolved Jul 22, 2026
This incident has been resolved.
The issue has been identified and a fix is being implemented.
We are investigating an outage affecting features such as document creation in claude.ai, Cowork Remote, Claude Code, Claude Code on the Web, Claude Tag, and Claude Design
Frequently Asked Questions
Is Claude down right now?
Check the status indicator at the top of this page. It pulls directly from Anthropic's official status page. If Anthropic is experiencing any issues, you'll see it reflected here. This real-time monitoring helps teams quickly identify whether performance problems are caused by Anthropic infrastructure or their own systems.
What does this Anthropic status page track?
This page tracks Claude, Claude API, Claude Code, Claude Sonnet, and Claude Opus using data from Anthropic's official status page. You can see current component health, active incidents, and a history of past issues. This visibility is crucial for teams building resilient AI applications that need to route around provider outages.
How often is Anthropic status updated here?
We check Anthropic's status page every 60 seconds to ensure you get near real-time status updates. How quickly issues show up here depends on how fast Anthropic updates their own official status. For production systems that need instant failover, Bifrost can automatically detect and route around degraded providers.
Why monitor Anthropic status?
Anthropic outages often matter most to engineering, agent, and internal tooling use cases where Claude is deeply embedded into day-to-day developer workflows. Real-time status monitoring enables proactive incident response and helps teams decide when to route traffic to alternative providers for maximum uptime.
What should I do when Claude or Anthropic has an outage?
When Anthropic experiences an outage, the best practice is automatic failover to alternative AI providers. Bifrost is an open-source AI gateway that automatically detects Anthropic degradation and routes LLM traffic to healthy alternatives like OpenAI (GPT-4), Google Gemini, Cohere, keeping your application running with zero manual intervention. This intelligent routing ensures your users never experience downtime from a single provider's issues.
How can I prevent Anthropic downtime from affecting my application?
Production AI applications should never depend on a single provider. Bifrost AI Gateway provides automatic multi-provider failover, intelligent load balancing, and health-based routing. When Anthropic degrades, Bifrost instantly routes requests to operational alternatives while maintaining API compatibility. This architecture approach is used by teams running mission-critical AI features.
What are common causes of Anthropic outages and degraded performance?
Based on incident history, Anthropic issues most frequently affect Claude Code, claude.ai, and Claude API (api.anthropic.com). Common causes include infrastructure scaling issues, regional cloud provider problems, API gateway overload, and deployment errors. Teams using Bifrost can configure automatic routing rules based on component-level status to minimize impact.
Alternative Providers for Automatic Failover
When Anthropic experiences issues, Bifrost AI Gateway can automatically route your LLM traffic to these alternatives
💡 Build resilient AI apps: Configure Bifrost to automatically detect Anthropic outages and route requests to healthy alternatives. This multi-provider approach ensures your application maintains uptime even when individual providers experience issues. Learn more about Bifrost AI Gateway
Anthropic Models & Pricing
Anthropic offers 24 models across 1 mode (24 chat)