perf(prometheus): parallelize budget metrics, fix caching bug, reduce CPU by ~40% (#20544)

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
@@ -1188,28 +1189,34 @@ 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,
+        results = 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,
+            ),
+            return_exceptions=True,
         )
+        for i, r in enumerate(results):
+            if isinstance(r, Exception):
+                verbose_logger.debug(
+                    f"[Non-Blocking] Prometheus: Budget metric lookup {['key', 'team', 'user'][i]} failed: {r}"
+                )
 
     def _increment_top_level_request_and_spend_metrics(
         self,
@@ -2898,12 +2905,14 @@ class PrometheusLogger(CustomLogger):
             max_budget=max_budget,
         )
         try:
+            # Note: Setting check_db_only=True bypasses cache and hits DB on every request,
+            # causing huge latency increase and CPU spikes. Keep check_db_only=False.
             user_info = await get_user_object(
                 user_id=user_id,
                 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(

poetry.lock

@@ -8531,8 +8531,4 @@ utils = ["numpydoc"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4.0"
-<<<<<<< litellm_oss_staging_02_04_2026
-content-hash = "797603dcfef0a79781c7d3cba5dfe18f6aea4aa792220f47487ebc7bd04ae2e3"
-=======
 content-hash = "e5447e14dd37e324ac07a8fc6286d27e9a0d355ed93ebb24fc11e3f5df12fd3e"
->>>>>>> main