From 9c5ff9d3360e6a858391c411c1bf0cfa72552c0f Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Thu, 14 May 2026 22:34:55 +0000 Subject: [PATCH] perf(dynamic_rate_limiter): only resolve provider when rate limit hit Co-authored-by: Yassin Kortam --- litellm/proxy/hooks/dynamic_rate_limiter.py | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/litellm/proxy/hooks/dynamic_rate_limiter.py b/litellm/proxy/hooks/dynamic_rate_limiter.py index c15e4bd7068..b9e2bd12ecf 100644 --- a/litellm/proxy/hooks/dynamic_rate_limiter.py +++ b/litellm/proxy/hooks/dynamic_rate_limiter.py @@ -218,11 +218,11 @@ class _PROXY_DynamicRateLimitHandler(CustomLogger): ) = await self.check_available_usage( model=data["model"], priority=key_priority ) - resolved_model, llm_provider = resolve_llm_provider_for_rate_limit( - data.get("model") - ) ### CHECK TPM ### if available_tpm is not None and available_tpm == 0: + resolved_model, llm_provider = resolve_llm_provider_for_rate_limit( + data.get("model") + ) raise ProxyRateLimitError( detail={ "error": "Key={} over available TPM={}. Model TPM={}, Active keys={}".format( @@ -238,6 +238,9 @@ class _PROXY_DynamicRateLimitHandler(CustomLogger): ) ### CHECK RPM ### elif available_rpm is not None and available_rpm == 0: + resolved_model, llm_provider = resolve_llm_provider_for_rate_limit( + data.get("model") + ) raise ProxyRateLimitError( detail={ "error": "Key={} over available RPM={}. Model RPM={}, Active keys={}".format(