From 05fbb78a3819af16d0d99a7e9e37f3eab652fd7e Mon Sep 17 00:00:00 2001
From: Alexsander Hamir <alexsanderhamirgomesbaptista@gmail.com>
Date: Thu, 5 Feb 2026 15:33:44 -0800
Subject: [PATCH] perf(prometheus): parallelize budget metric lookups with
 asyncio.gather

Replace sequential await of key, team, and user budget metric lookups
with asyncio.gather() so they run in parallel. Reduces latency from
T_key + T_team + T_user to max(T_key, T_team, T_user) when lookups
hit DB or cache.
---
 litellm/integrations/prometheus.py | 45 +++++++++++++++---------------
 1 file changed, 23 insertions(+), 22 deletions(-)

diff --git a/litellm/integrations/prometheus.py b/litellm/integrations/prometheus.py
index 00c38eac188..359e902a50b 100644
--- a/litellm/integrations/prometheus.py
+++ b/litellm/integrations/prometheus.py
@@ -1,6 +1,7 @@
 # used for /metrics endpoint on LiteLLM Proxy
 #### What this does ####
 #    On success, log events to Prometheus
+import asyncio
 import os
 import sys
 from datetime import datetime, timedelta
@@ -1188,27 +1189,27 @@ class PrometheusLogger(CustomLogger):
         _user_spend = _metadata.get("user_api_key_user_spend", None)
         _user_max_budget = _metadata.get("user_api_key_user_max_budget", None)
 
-        await self._set_api_key_budget_metrics_after_api_request(
-            user_api_key=user_api_key,
-            user_api_key_alias=user_api_key_alias,
-            response_cost=response_cost,
-            key_max_budget=_api_key_max_budget,
-            key_spend=_api_key_spend,
-        )
-
-        await self._set_team_budget_metrics_after_api_request(
-            user_api_team=user_api_team,
-            user_api_team_alias=user_api_team_alias,
-            team_spend=_team_spend,
-            team_max_budget=_team_max_budget,
-            response_cost=response_cost,
-        )
-
-        await self._set_user_budget_metrics_after_api_request(
-            user_id=user_id,
-            user_spend=_user_spend,
-            user_max_budget=_user_max_budget,
-            response_cost=response_cost,
+        await asyncio.gather(
+            self._set_api_key_budget_metrics_after_api_request(
+                user_api_key=user_api_key,
+                user_api_key_alias=user_api_key_alias,
+                response_cost=response_cost,
+                key_max_budget=_api_key_max_budget,
+                key_spend=_api_key_spend,
+            ),
+            self._set_team_budget_metrics_after_api_request(
+                user_api_team=user_api_team,
+                user_api_team_alias=user_api_team_alias,
+                team_spend=_team_spend,
+                team_max_budget=_team_max_budget,
+                response_cost=response_cost,
+            ),
+            self._set_user_budget_metrics_after_api_request(
+                user_id=user_id,
+                user_spend=_user_spend,
+                user_max_budget=_user_max_budget,
+                response_cost=response_cost,
+            ),
         )
 
     def _increment_top_level_request_and_spend_metrics(
@@ -2903,7 +2904,7 @@ class PrometheusLogger(CustomLogger):
                 prisma_client=prisma_client,
                 user_api_key_cache=user_api_key_cache,
                 user_id_upsert=False,
-                check_db_only=True,
+                check_db_only=False,
             )
         except Exception as e:
             verbose_logger.debug(