From e90971a7070d7fbabbeb1c1b3f68feb0a94402a0 Mon Sep 17 00:00:00 2001 From: fpagny Date: Fri, 4 Apr 2025 11:00:14 +0200 Subject: [PATCH 1/2] fix(genapi): improve limit value redirection visibility --- pages/generative-apis/reference-content/rate-limits.mdx | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/pages/generative-apis/reference-content/rate-limits.mdx b/pages/generative-apis/reference-content/rate-limits.mdx index 92522e856d..3c3d1ae3d4 100644 --- a/pages/generative-apis/reference-content/rate-limits.mdx +++ b/pages/generative-apis/reference-content/rate-limits.mdx @@ -18,7 +18,8 @@ Any model served through Scaleway Generative APIs gets rate limited based on: - Queries per minute (HTTP requests) Base limits apply if you registered a valid payment method, and are increased automatically if you also [verify your identity](/account/how-to/verify-identity/). -Limit values are detailed in [Organization quotas for Generative APIs](/organizations-and-projects/additional-content/organization-quotas/#generative-apis). + +**Exact Limit values are detailed** in [Organization quotas for Generative APIs](/organizations-and-projects/additional-content/organization-quotas/#generative-apis). If you created a Scaleway Account but did not register a valid payment method, stricter limits apply to ensure usage stays within Free Tier only. From 6c8b88d1a33448f954d3dd4fd6e9a60f770c487e Mon Sep 17 00:00:00 2001 From: fpagny Date: Fri, 4 Apr 2025 11:10:03 +0200 Subject: [PATCH 2/2] feat(genapi): add concurrent request limits --- pages/generative-apis/reference-content/rate-limits.mdx | 1 + 1 file changed, 1 insertion(+) diff --git a/pages/generative-apis/reference-content/rate-limits.mdx b/pages/generative-apis/reference-content/rate-limits.mdx index 3c3d1ae3d4..578b5408e8 100644 --- a/pages/generative-apis/reference-content/rate-limits.mdx +++ b/pages/generative-apis/reference-content/rate-limits.mdx @@ -16,6 +16,7 @@ dates: Any model served through Scaleway Generative APIs gets rate limited based on: - Tokens per minute (total input and output tokens) - Queries per minute (HTTP requests) +- Concurrent requests (total active HTTP session at the same time) Base limits apply if you registered a valid payment method, and are increased automatically if you also [verify your identity](/account/how-to/verify-identity/).