Is Claude Code down right now?

Yes. HostTracker lets you add any URL - including third-party services you depend on, not just your own website - as a monitored target, and notifies you automatically the moment it becomes unreachable. Before sending an alert, HostTracker re-verifies a failure from multiple locations in its 300+-location network, so you're notified about real, confirmed outages rather than a single location's momentary blip. The free plan checks two monitors every 30 minutes indefinitely at no cost; paid plans check as often as once a minute, with alerts available through SMS, email, voice call, and several messenger apps.

Run the live check at the top of this page - it tests api.anthropic.com from HostTracker's 300+ monitoring locations at once and tells you within seconds whether Claude Code is reachable for everyone or only failing for you.

Run the live check at the top of this page - it tests api.anthropic.com from HostTracker's 300+ monitoring locations at once and tells you within seconds whether Claude Code is reachable for everyone or only failing for you.

A 529 response means Anthropic's API is overloaded and can't accept your request right now, which is a capacity signal rather than a sign anything is broken on your machine. It's distinct from a network failure or an auth error - the connection succeeded and reached Anthropic's servers, and those servers are the ones under pressure. It usually clears within minutes during a demand spike, and retrying after a short pause is normally enough. If it persists for an extended period, the live check on this page confirms whether it's a wider incident.

Not necessarily either way - Claude Code and the claude.ai web app both call Anthropic's API, but often through different paths and limits, so one can be degraded while the other is healthy. A CLI session failing while the website loads normally usually points at something specific to API access - a token, a rate limit, a regional route - rather than a platform-wide incident. Check /en/is-claude-down for the web app specifically; this page tracks the API endpoint Claude Code itself depends on.

Usually not. An authentication or OAuth failure blocks your session from reaching the API but doesn't necessarily mean the API is unreachable - it's more often a stale token, an expired login, or a permissions problem on the account side. Signing out and back in through the CLI resolves most of these. If sign-in fails for many people at once and this page also shows the API unreachable, that points at a genuine authentication-service incident instead.

Regional routing is a real cause of intermittent failures separate from any incident at Anthropic. A misconfigured DNS resolver, a corporate proxy, or a routing problem between your ISP and Anthropic's infrastructure can make api.anthropic.com unreachable from one location while it works normally elsewhere. Testing the endpoint from multiple independent locations, which is what this page does, is the fastest way to tell a local network problem from a real outage affecting everyone.