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

# Rate Limits

> How the API limits request rate, and how to handle being throttled

GC AI rate-limits the API in two tiers. **Inference** endpoints (the model-backed calls) are limited tightly. Everything else (listing, creating, and updating projects, playbooks, files, and so on) gets a far more forgiving limit.

<Note>
  Limits are intentionally conservative during the free beta, where the rate limit is the main guardrail on usage. They will loosen as the API moves toward general availability.
</Note>

## The two tiers

| Tier                | Endpoints                                                                   | Limit (beta)                                             |
| ------------------- | --------------------------------------------------------------------------- | -------------------------------------------------------- |
| **Inference**       | `POST /chat/completions`, `POST /playbooks/{id}/run`                        | \~1 request / minute per organization, with a burst of 3 |
| **Everything else** | All other endpoints (files, folders, projects, playbooks CRUD, profiles, …) | 120 requests / minute per organization                   |

The inference limit is a window of **3 requests per 180 seconds**: you can spend a burst of 3 right away, after which it averages out to roughly one per minute.

## What counts against the limit

Limits apply **per organization**, and within that **per API key**. GC AI checks both on every request, and whichever is exhausted first blocks it:

* The **per-organization** limit is the binding ceiling. It is shared across every key the organization holds, so minting extra keys does not raise your total throughput.
* The **per-key** limit keeps one integration from monopolizing the organization's budget. During the beta it matches the org limit; as limits rise toward GA it becomes the per-integration sub-limit.

## When you exceed a limit

A throttled request returns **`429 Too Many Requests`**:

```json theme={null}
{
  "error": "Rate limit exceeded",
  "code": "RATE_LIMITED"
}
```

It also carries headers describing the limit and when to retry:

| Header                | Meaning                                        |
| --------------------- | ---------------------------------------------- |
| `Retry-After`         | Seconds to wait before retrying.               |
| `RateLimit-Limit`     | The request quota for the window that was hit. |
| `RateLimit-Remaining` | Requests remaining in the current window.      |
| `RateLimit-Reset`     | Seconds until the quota resets.                |

Honor `Retry-After`: wait that many seconds before sending the next request. For batch workloads, use [fire-and-forget](/api-reference/concepts/async-jobs#waiting-inline-vs-fire-and-forget) and pace your enqueues rather than retrying in a tight loop.

## Related

* [Asynchronous Requests](/api-reference/concepts/async-jobs): inference calls are jobs; pace batches with fire-and-forget.
* [API Introduction](/api-reference/introduction): base URL, authentication, and a first request.