Outage in Anthropic

Elevated errors on the API, Console and Claude.ai

Resolved Major
June 12, 2025 - Started 1 day ago - Lasted about 3 hours
Official incident page

Need to monitor Anthropic outages?
Stay on top of outages with IsDown. Monitor the official status pages of all your vendors, SaaS, and tools, including Anthropic, and never miss an outage again.
Start Free Trial

Outage Details

We are currently investigating an issue which is resulting in significantly elevated HTTP 503 errors across Anthropic services. We will provide updates as soon as possible.
Latest Updates ( sorted recent to last )
RESOLVED 1 day ago - at 06/12/2025 08:55PM

This incident has been resolved.

MONITORING 1 day ago - at 06/12/2025 08:44PM

We have confirmed that all success rates have returned to normal at this time, and are closely monitoring to ensure no further issues.

IDENTIFIED 1 day ago - at 06/12/2025 08:26PM

We are seeing success rates return to normal across the Anthropic API, Console, and Claude.ai. Our engineers are continuing to work to ensure no further recurrences of impact.

IDENTIFIED 1 day ago - at 06/12/2025 07:52PM

Our engineers are continuing to work to recover public API success rates, though text-only requests to Claude.ai should return responses as expected. We will continue to provide updates as we make progress towards full recovery.

IDENTIFIED 1 day ago - at 06/12/2025 07:20PM

We are seeing increased rates of errors on requests to all models, and are continuing to work to mitigate impact from the ongoing GCP disruption. We will provide additional updates as soon as possible.

IDENTIFIED 1 day ago - at 06/12/2025 06:54PM

Image and file uploads on the API or through Claude.ai are unavailable, as a result of the ongoing issue impacting GCP. Requests involving text-only are likely to be successful, but we are continuing to await further updates regarding resolution of the underlying platform issue.

IDENTIFIED 1 day ago - at 06/12/2025 06:41PM

We have identified that the current elevated error rates are a result of an ongoing outage impacting GCP, and associated services. We will continue to provide updates as we work to resolve these ongoing impacts.

INVESTIGATING 1 day ago - at 06/12/2025 06:23PM

We are currently investigating an issue which is resulting in significantly elevated HTTP 503 errors across Anthropic services. We will provide updates as soon as possible.

source IsDown Possible Outage Indicated by User Reports Reports started 6 minutes before official outage was reported

Be the First to Know When Vendors Go Down

With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.

Start free trial

No credit card required · Cancel anytime · 4200 services available

Integrations with Slack Microsoft Teams Google Chat Datadog PagerDuty Zapier Discord Webhook