> ## Documentation Index
> Fetch the complete documentation index at: /llms.txt
> Use this file to discover all available pages before exploring further.

# Rate limits

> How many requests you can make, and how to stay within the limit.

Each API key is limited to about **1,200 requests per minute**, with room for short bursts. Requests over the limit are refused with `429`:

```http
HTTP/1.1 429 Too Many Requests
Retry-After: 2
```

Wait for the number of seconds in `Retry-After`, then try again.

## Staying within the limit

> [accordion] Page with the largest page size
>
> Use `limit=100` on lists rather than many small pages.

> [accordion] Do not poll fast
>
> Checking a conversation every second for a reply uses 60 requests a minute for one user. Poll slowly, and stop when the conversation is closed or the screen is not in use.

> [accordion] Cache what does not change
>
> Store each customer's Cerium `id` after you create them. Do not call `POST /customers` before every message.

> [accordion] Back off on 429
>
> Do not retry in a tight loop. Use exponential backoff with jitter, as in the [retry pattern](/guides/idempotency.md#a-retry-pattern).

> [accordion] Use separate keys for separate systems
>
> The limit applies per key, so a batch job on its own key cannot slow your live traffic.

> [!NOTE]
>
> If you expect sustained traffic above this limit, contact [support](/support.md) before launch.

Requests may also be refused if the body is larger than 1 MB (`413`).
