# Status and reliability

> How the gateway handles upstream failures, and what to do when something is degraded.

_Source: https://aiprimetech.io/docs/resources/status/ · Home > Docs > Resources_


## How failover works

Requests are distributed across upstream capacity. When one upstream returns an error or is overloaded, traffic moves to another rather than surfacing a hard failure — which is why a `529` here is rarer than calling a single provider directly.


## What each failure means for you

| You see | Where the fault is | What to do |
|---|---|---|
| `529` overloaded | Upstream capacity | Retry with backoff; usually clears in seconds |
| `500` | Gateway | Retry once, then report with the request id |
| `429` | Your account's concurrency | Reduce parallelism — [Rate limits](/docs/api-reference/rate-limits/) |
| Slow first token | Upstream queueing under load | Expected during peaks; streaming makes it visible sooner |


## Building for degradation

- Retry `429`, `500`, `502`, `503` and `529` with exponential backoff and jitter.
- Keep a fallback model configured — degrading from Opus to Sonnet beats returning an error.
- Set timeouts so a stalled request cannot hold a worker indefinitely.
- Run the `/v1/models` health check in CI so a broken credential is caught before deploy.

For an incident affecting your account, contact [support@claudeapikey.dev](mailto:support@claudeapikey.dev) with timestamps and a request id.

- [Errors](https://aiprimetech.io/docs/api-reference/errors/) — Full status reference
- [Best practices](https://aiprimetech.io/docs/guides/best-practices/) — Resilient clients


---
_ClaudeAPIKey.dev is an independently operated, Anthropic-compatible API gateway. Not affiliated with Anthropic._