diff --git a/litellm/litellm_core_utils/core_helpers.py b/litellm/litellm_core_utils/core_helpers.py
index 9cb0a00d9fc..00695cbfb5b 100644
--- a/litellm/litellm_core_utils/core_helpers.py
+++ b/litellm/litellm_core_utils/core_helpers.py
@@ -351,9 +351,9 @@ def filter_exceptions_from_params(data: Any, max_depth: int = 20) -> Any:
     # Skip callable objects (functions, methods, lambdas) but not classes (type objects)
     if callable(data) and not isinstance(data, type):
         return None
-    # Skip known non-serializable object types (Logging, etc.)
+    # Skip known non-serializable object types (Logging, Router, etc.)
     obj_type_name = type(data).__name__
-    if obj_type_name in ["Logging", "LiteLLMLoggingObj"]:
+    if obj_type_name in ["Logging", "LiteLLMLoggingObj", "Router"]:
         return None
 
     if isinstance(data, dict):
diff --git a/litellm/rag/main.py b/litellm/rag/main.py
index 0ccbb435e53..620097f83dd 100644
--- a/litellm/rag/main.py
+++ b/litellm/rag/main.py
@@ -198,6 +198,10 @@ async def _execute_query_pipeline(
     """
     Execute the RAG query pipeline.
     """
+    # Extract router from kwargs - use it for completion if available
+    # to properly resolve virtual model names
+    router: Optional["Router"] = kwargs.pop("router", None)
+
     # 1. Extract query from last user message
     query_text = RAGQuery.extract_query_from_messages(messages)
     if not query_text:
@@ -233,12 +237,21 @@ async def _execute_query_pipeline(
     context_message = RAGQuery.build_context_message(context_chunks)
     modified_messages = messages[:-1] + [context_message] + [messages[-1]]
 
-    response = await litellm.acompletion(
-        model=model,
-        messages=modified_messages,
-        stream=stream,
-        **kwargs,
-    )
+    # Use router if available to properly resolve virtual model names
+    if router is not None:
+        response = await router.acompletion(
+            model=model,
+            messages=modified_messages,
+            stream=stream,
+            **kwargs,
+        )
+    else:
+        response = await litellm.acompletion(
+            model=model,
+            messages=modified_messages,
+            stream=stream,
+            **kwargs,
+        )
 
     # 5. Attach search results to response
     if not stream and isinstance(response, ModelResponse):