# Rate limit

> A rate limit caps how many requests an account may send per minute. It protects shared capacity and is the reason a burst of parallel calls can fail while the same calls spread out succeed.

A well-behaved client treats the limit as part of the contract rather than an error: it reads the response header that says how long to wait and backs off, instead of retrying immediately and making the queue worse.

Limits usually scale with the plan rather than being removed by it.

## On eroq

Per minute and per key — 60 chat completions, 20 images, 6 video or speech renders — multiplied by the plan from Creator upward (2× Creator, 4× Studio, 6× Team, 8× Agency). Hobby raises your credits and clip length but not this ceiling. Over the line you get a 429 with `rate_limit_exceeded` and a `Retry-After` header in seconds, uncharged. An admin can also cap an individual member to a share of the workspace allowance.

## FAQ

### What happens when I hit the limit?

The request returns a 429 with the code `rate_limit_exceeded` and a `Retry-After` header giving the seconds to wait. Nothing is charged, so back off on the header rather than guessing.

### Does a paid plan remove the limit?

It multiplies it rather than removing it, and only from Creator upward — 2× there, up to 8× on Agency. Hobby leaves the per-minute ceiling where the free tier has it, and there is no unlimited tier.

### Can one teammate use up the whole allowance?

They can, unless an admin gives them a share. Each member can be capped to a percentage of the workspace allowance, and separately to a monthly credit ceiling.

## Related

- https://eroq.ai/docs/rate-limits — Rate limit reference
- https://eroq.ai/glossary/api-key — API key
- https://eroq.ai/glossary/workspace — Workspace

---

This page as HTML: https://eroq.ai/glossary/rate-limit · Studio: https://eroq.ai/studio · Docs: https://eroq.ai/docs · Machine index: https://eroq.ai/llms.txt