# Is Claude API Down? Anthropic Status and Error Checks

TL;DR: Check whether a Claude or Anthropic API failure looks like provider overload, network reset, invalid auth, or an application-side retry problem.

Official status: https://status.anthropic.com/
Public endpoint: https://api.anthropic.com/v1/messages
Run diagnosis: https://llmping.app/#diagnose

## Honest boundary

llmping does not ping user API keys and does not claim fake real-time provider status. Use the checks below to separate outage symptoms from key, quota, permission, and runtime problems.

## Historical uptime

llmping samples provider public endpoints and official status feeds every 5 minutes with a Cloudflare Worker and stores real samples in D1. The status page displays 7, 30, and 90 day public endpoint uptime once samples exist.

Uptime API: https://llmping-uptime-worker.stcatzlee.workers.dev/api/uptime?provider=anthropic

## Quick checks

- 529 overloaded_error points to provider capacity pressure.
- ECONNRESET is a transport failure and can come from proxies or serverless timeouts.
- 401/403 class errors are normally account, key, or permission issues.
- Compare one short request against one streaming request before blaming the provider.

## cURL test command

```bash
curl -i https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model":"claude-3-5-haiku-latest","max_tokens":16,"messages":[{"role":"user","content":"ping"}]}'
```

## Related pages

- https://llmping.app/errors/anthropic/529/
- https://llmping.app/errors/claude/econnreset/
- https://llmping.app/errors/openai/429/