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

# Rate limits

> Per-key limits, the headers that report them, and what to do when you hit one.

Every API key has its own limits, set when the key is created (console, **API keys**). Every authenticated response
reports them in the [IETF draft](https://datatracker.ietf.org/doc/draft-ietf-httpapi-ratelimit-headers/) headers:

```http theme={null}
RateLimit-Policy: "minute";q=600;w=60, "day";q=200000;w=86400
RateLimit: "minute";r=599;t=41
```

| Policy | Counts |
| - | - |
| `minute`, `day` | Creating runs, uploads and catalog reads. |
| `poll` | Reading runs (`GET /v1/runs/{id}`), so polling never uses your create quota. |

When a limit is reached the API answers `429 RATE_LIMITED` with `Retry-After`. Organizations have no limit of their own
on runs in flight or waiting. If the whole service has too many runs waiting, new runs get `503 SERVICE_UNAVAILABLE` with
`Retry-After`, before anything is held; retry with the same `Idempotency-Key`. See [Errors](/docs/api-reference/errors.md).

Spend is limited separately: give each agent its own key with a spend cap ([Pricing and billing](/docs/concepts/pricing.md)).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.