# Production best practices

> What to get right before an integration carries real traffic.

_Source: https://aiprimetech.io/docs/guides/best-practices/ · Home > Docs > Working with the API_


## Reliability

- **Retry the right codes.** `429`, `500`, `502`, `503`, `529` with exponential backoff and jitter. Never blind-retry `400`, `401`, `402` or `403`.
- **Set timeouts.** A long generation can legitimately take minutes; a hung socket should not take your worker with it. 120s is a reasonable ceiling for non-streaming calls.
- **Cap concurrency** with a semaphore rather than firing everything and retrying rejections.
- **Have a fallback model.** If your primary is overloaded, degrading to a smaller model beats returning an error.


## Cost

- Set `max_tokens` on every call. It is a spending cap, not a hint.
- Route by task — see [Cost control](/docs/guides/cost-control/).
- Turn on [prompt caching](/docs/guides/prompt-caching/) for stable prefixes.
- Log `usage` per request with a task label so you can attribute spend later.


## Security

- Keys live in environment variables or a secret manager — never in the repo, never in a client bundle.
- One key per service, so revocation is surgical.
- Never build prompts by string-concatenating untrusted user input with instructions; keep user content in a `user` message and instructions in `system`.
- Treat model output as untrusted. Do not `eval` it, do not run generated SQL against a writable role.


## Observability

- Log model, latency, `usage`, `stop_reason` and your own task type for every call.
- Alert on the `stop_reason: max_tokens` rate — a rise means answers are being truncated.
- Track cost per task type, not just total. Totals hide which workload regressed.

> The highest-value alert is on truncation, not errors. A truncated answer returns HTTP 200 and looks fine to your monitoring while being wrong to the user.

- [Errors](https://aiprimetech.io/docs/api-reference/errors/) — Retry semantics
- [Rate limits](https://aiprimetech.io/docs/api-reference/rate-limits/) — Concurrency
- [Cost control](https://aiprimetech.io/docs/guides/cost-control/) — Spend management


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