From 2f4b6cfcacea7ff13a339953403786d415269623 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 4 Mar 2026 20:32:51 +0000 Subject: [PATCH] Update quota docs: burst capacity from 10 to 20 generations Co-Authored-By: Niels Swimberghe <3382717+Swimburger@users.noreply.github.com> --- fern/products/sdks/how-it-works.mdx | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fern/products/sdks/how-it-works.mdx b/fern/products/sdks/how-it-works.mdx index 396ba90f3..b40add2d1 100644 --- a/fern/products/sdks/how-it-works.mdx +++ b/fern/products/sdks/how-it-works.mdx @@ -68,10 +68,10 @@ Cloud (remote) generation uses a [leaky bucket](https://en.wikipedia.org/wiki/Le | Parameter | Value | | --- | --- | -| Burst capacity | 10 generations | +| Burst capacity | 20 generations | | Refill rate | 5 generations per minute | -You can run up to 10 generations in quick succession. Fern then replenishes your allowance at 5 generations per minute, so if you hit the limit, subsequent requests will be throttled until enough capacity is restored. In practice, this only affects automated workflows that trigger many generations in a tight loop — occasional manual runs won't come close to the limit. +You can run up to 20 generations in quick succession. Fern then replenishes your allowance at 5 generations per minute, so if you hit the limit, subsequent requests will be throttled until enough capacity is restored. In practice, this only affects automated workflows that trigger many generations in a tight loop — occasional manual runs won't come close to the limit. Rate limits apply only to cloud generation. [Local generation](/learn/sdks/deep-dives/self-hosted) using `--local` isn't subject to any quotas.