From 24e80ba3a915a3cfc9f80a6a114a2f2ea443017c Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Tue, 12 May 2026 03:14:14 +0000 Subject: [PATCH] perf(proxy/hooks): defer provider resolution to over-limit branches --- 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 f769a03c5c6..4ae530ee05b 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 ProxyHTTPRateLimitError( status_code=429, detail={ @@ -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 ProxyHTTPRateLimitError( status_code=429, detail={