From 3c01a943c7662702aaab67bc03f890e04d8c640d Mon Sep 17 00:00:00 2001
From: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
Date: Sat, 21 Feb 2026 14:59:35 -0800
Subject: [PATCH] fix(logging): preserve pass-through endpoint response_cost in
 async_success_handler

Two places in the logging pipeline were overwriting response_cost that
pass-through handlers (Gemini/Vertex) had already calculated:

1. _process_hidden_params_and_response_cost fell through to
   _response_cost_calculator which returns None for pass-through calls
2. async_success_handler pass-through branch unconditionally set
   response_cost = None (introduced in PR #19887)

Now both places check if response_cost is already set before overwriting.
---
 litellm/litellm_core_utils/litellm_logging.py | 38 ++++++++++++-------
 1 file changed, 24 insertions(+), 14 deletions(-)

diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py
index 64f1f9c72c2..56a22af3c29 100644
--- a/litellm/litellm_core_utils/litellm_logging.py
+++ b/litellm/litellm_core_utils/litellm_logging.py
@@ -1636,6 +1636,10 @@ class Logging(LiteLLMLoggingBaseClass):
             self.model_call_details["response_cost"] = 0.0
         elif "response_cost" in hidden_params:
             self.model_call_details["response_cost"] = hidden_params["response_cost"]
+        elif self.model_call_details.get("response_cost") is not None:
+            # Preserve response_cost if already calculated (e.g., by pass-through
+            # handlers like Gemini/Vertex which call completion_cost directly)
+            pass
         else:
             self.model_call_details["response_cost"] = self._response_cost_calculator(
                 result=logging_result
@@ -2496,23 +2500,29 @@ class Logging(LiteLLMLoggingBaseClass):
 
             self.model_call_details["async_complete_streaming_response"] = result
 
-            # cost calculation not possible for pass-through
-            self.model_call_details["response_cost"] = None
+            # Only set response_cost to None if not already calculated by
+            # pass-through handlers (e.g. Gemini/Vertex handlers already
+            # compute cost via completion_cost)
+            if self.model_call_details.get("response_cost") is None:
+                self.model_call_details["response_cost"] = None
 
-            ## STANDARDIZED LOGGING PAYLOAD
-            self.model_call_details[
-                "standard_logging_object"
-            ] = self._build_standard_logging_payload(
-                result, start_time, end_time
-            )
-
-            # print standard logging payload
-            if (
-                standard_logging_payload := self.model_call_details.get(
+            # Only build standard_logging_object if not already built by
+            # _success_handler_helper_fn
+            if self.model_call_details.get("standard_logging_object") is None:
+                ## STANDARDIZED LOGGING PAYLOAD
+                self.model_call_details[
                     "standard_logging_object"
+                ] = self._build_standard_logging_payload(
+                    result, start_time, end_time
                 )
-            ) is not None:
-                emit_standard_logging_payload(standard_logging_payload)
+
+                # print standard logging payload
+                if (
+                    standard_logging_payload := self.model_call_details.get(
+                        "standard_logging_object"
+                    )
+                ) is not None:
+                    emit_standard_logging_payload(standard_logging_payload)
         callbacks = self.get_combined_callback_list(
             dynamic_success_callbacks=self.dynamic_async_success_callbacks,
             global_callbacks=litellm._async_success_callback,