From 2b7886f77c788b5e4100e347cb8b5adcbcb1d3af Mon Sep 17 00:00:00 2001 From: fpagny Date: Thu, 16 Jan 2025 12:57:02 +0100 Subject: [PATCH] Update rate-limits.mdx Update embeddings related quotas. Add detail about Free Tier quotas limitations. --- .../reference-content/rate-limits.mdx | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/ai-data/generative-apis/reference-content/rate-limits.mdx b/ai-data/generative-apis/reference-content/rate-limits.mdx index 6dddaf8b14..bac5f93d8e 100644 --- a/ai-data/generative-apis/reference-content/rate-limits.mdx +++ b/ai-data/generative-apis/reference-content/rate-limits.mdx @@ -17,9 +17,13 @@ Any model served through Scaleway Generative APIs gets limited by: - Tokens per minute - Queries per minute + +These limits only apply if you created a Scaleway Account and registered a valid payment method. Otherwise, stricter limits apply to ensure usage stays within Free Tier only. + + ### Chat models -| Model string | Requests per minute | Tokens per minute | +| Model string | Requests per minute | Total Tokens per minute | |-----------------|-----------------|-----------------| | `llama-3.1-8b-instruct` | 300 | 100K | | `llama-3.1-70b-instruct` | 300 | 100K | @@ -29,10 +33,10 @@ Any model served through Scaleway Generative APIs gets limited by: ### Embedding models -| Model string | Requests per minute | Tokens per minute | +| Model string | Requests per minute | Input Tokens per minute | |-----------------|-----------------|-----------------| -| `sentence-t5-xxl` | 600 | 1M | -| `bge-multilingual-gemma2` | 600 | 1M | +| `sentence-t5-xxl` | 100 | 200K | +| `bge-multilingual-gemma2` | 100 | 200K | ## Why do we set rate limits? @@ -41,4 +45,4 @@ These limits safeguard against abuse or misuse of Scaleway Generative APIs, help ## How can I increase the rate limits? We actively monitor usage and will improve rates based on feedback. -If you need to increase your rate limits, contact us via the support team, providing details on the model used and specific use case. \ No newline at end of file +If you need to increase your rate limits, contact us via the support team, providing details on the model used and specific use case.