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.ai, Claude API (api.anthropic.com), and Claude Code.
[ 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
Connection failures for organizations restricting GitHub access by IP address
May 6, 2026 · Resolved May 7, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
We have identified an issue affecting organizations that restrict GitHub access by source IP address. A recent infrastructure change altered the IP addresses Anthropic uses for outbound connections to GitHub, which may cause Claude Code remote sessions, GitHub Enterprise plugin syncing, and Claude Security to fail. We are reverting the change to restore the previous IP ranges; no allowlist changes will be needed on your side. We will post an update once the fix is deployed.
Elevated errors on Claude Opus 4.7
May 7, 2026 · Resolved May 7, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
We are currently investigating this issue.
Elevated errors across multiple models
May 6, 2026 · Resolved May 6, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
We are currently investigating this issue.
Elevated errors on Claude Opus 4.5 and Sonnet 4.5
May 4, 2026 · Resolved May 4, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
We are currently investigating this issue.
Elevated errors on Claude Opus 4.7
May 4, 2026 · Resolved May 4, 2026
This incident has been resolved.
The issue has been identified and a fix is being implemented.
Elevated errors on Claude Opus 4.5
May 4, 2026 · Resolved May 4, 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 continuing to investigate this issue.
+ 1 more updates
Elevated errors on Claude Haiku 4.5
Apr 30, 2026 · Resolved Apr 30, 2026
The incident has been resolved. Error rates were elevated between 5:20 PT / 12:48 PT and 6:48 PT / 13:48 PT.
We are currently investigating this issue.
claude.ai and API unavailable
Apr 30, 2026 · Resolved Apr 30, 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 Haiku 4.5
Apr 29, 2026 · Resolved Apr 29, 2026
The incident is resolved. The elevated error rate was between 05:37 PT / 12:37 UTC and 06:58 PT / 13:37 UTC.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Elevated errors on Claude Opus 4.7
Apr 28, 2026 · Resolved Apr 29, 2026
The incident is now resolved. The impact was between 16:25 PT / 23:25 UTC and 16:33 PT / 23:33 UTC.
We are currently investigating this issue.
Claude.ai unavailable and elevated errors on the API
Apr 28, 2026 · Resolved Apr 28, 2026
This incident has been resolved.
We are seeing success rates across all services return to normal, and are monitoring closely to prevent any further issues. Impact occurred from 17:34–18:52 UTC.
We are continuing to work to resolve the issues preventing users from accessing Claude.ai, and causing elevated authentication errors for requests to the API and Claude Code.
We have identified an issue resulting in elevated errors on the Anthropic API, as well as issues accessing Claude.ai, including log-in paths for Claude Code. We are working to resolve these issues, and will provide an update as soon as possible.
We are investigating an issue preventing users from reaching Claude.ai, and will provide an update as soon as possible.
Elevated errors on Claude Sonnet 4.5
Apr 28, 2026 · Resolved Apr 28, 2026
The incident has now been resolved. The timeline for the elevated errors was 6:22 PT / 13:22 UTC -> 6:39 PT / 13:39 UTC.
We are currently investigating this issue.
Elevated errors on Claude Haiku 4.5
Apr 28, 2026 · Resolved Apr 28, 2026
The incident has now been resolved. The elevated error rate for Haiku 4.5 was between 4:53 PT / 11:53 UTC and 5:36 PT / 12:44 UTC.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Claude Code Code Review was intermittently failing
Apr 28, 2026 · Resolved Apr 28, 2026
Claude Code Code Review intermittently wasn't starting sessions.
Elevated billing related errors on Claude.ai
Apr 27, 2026 · Resolved Apr 27, 2026
This incident has been resolved.
We are currently investigating this issue.
Investigated elevated errors and slower responses on claude.ai
Apr 25, 2026 · Resolved Apr 25, 2026
This incident has been resolved.
We are currently investigating this issue.
Elevated errors on Claude Opus 4.7
Apr 25, 2026 · Resolved Apr 25, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
The issue has been identified and a fix is being implemented.
Elevated errors on Claude Opus 4.7
Apr 25, 2026 · Resolved Apr 25, 2026
This incident has been resolved.
A fix has been implemented and we are monitoring the results.
We are currently investigating this issue.
Claude Code v2.1.120 Crashes on Startup
Apr 25, 2026 · Resolved Apr 25, 2026
This incident has been resolved.
We have identified an issue in Claude Code version 2.1.120 that causes a crash when resuming a prior session via the --resume or --continue flags. Auto-update will move affected clients back to 2.1.119 on next check, but you can always run `claude install 2.1.119`.
Elevated error rates on Claude Opus 4.7
Apr 25, 2026 · Resolved Apr 25, 2026
The issue affecting requests to Claude Opus 4.7 has been resolved. Impact occurred from 01:24–01:59 UTC.
A fix has been deployed for Claude Opus 4.7 and we are seeing success rates at normal levels. We are continuing to monitor, and ensure no further recurrence.
We are investigating elevated errors for requests to Claude Opus 4.7. We will provide an update as soon as possible.
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.ai, Claude API (api.anthropic.com), and Claude Code. 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