diff --git a/litellm/proxy/auth/route_checks.py b/litellm/proxy/auth/route_checks.py
index c75c1e66c..9496776a8 100644
--- a/litellm/proxy/auth/route_checks.py
+++ b/litellm/proxy/auth/route_checks.py
@@ -192,6 +192,10 @@ class RouteChecks:
             return True
         if "/langfuse/" in route:
             return True
+        if "/anthropic/" in route:
+            return True
+        if "/azure/" in route:
+            return True
         return False
 
     @staticmethod
diff --git a/litellm/proxy/vertex_ai_endpoints/google_ai_studio_endpoints.py b/litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py
similarity index 98%
rename from litellm/proxy/vertex_ai_endpoints/google_ai_studio_endpoints.py
rename to litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py
index c4a64fa21..0834102b3 100644
--- a/litellm/proxy/vertex_ai_endpoints/google_ai_studio_endpoints.py
+++ b/litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py
@@ -2,10 +2,8 @@
 What is this? 
 
 Provider-specific Pass-Through Endpoints
-"""
 
-"""
-1. Create pass-through endpoints for any LITELLM_BASE_URL/gemini/<endpoint> map to https://generativelanguage.googleapis.com/<endpoint>
+Use litellm with Anthropic SDK, Vertex AI SDK, Cohere SDK, etc.
 """
 
 import ast
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index 1551330d1..9d7c120a7 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -203,6 +203,9 @@ from litellm.proxy.openai_files_endpoints.files_endpoints import (
     router as openai_files_router,
 )
 from litellm.proxy.openai_files_endpoints.files_endpoints import set_files_config
+from litellm.proxy.pass_through_endpoints.llm_passthrough_endpoints import (
+    router as llm_passthrough_router,
+)
 from litellm.proxy.pass_through_endpoints.pass_through_endpoints import (
     initialize_pass_through_endpoints,
 )
@@ -233,9 +236,6 @@ from litellm.proxy.utils import (
     reset_budget,
     update_spend,
 )
-from litellm.proxy.vertex_ai_endpoints.google_ai_studio_endpoints import (
-    router as gemini_router,
-)
 from litellm.proxy.vertex_ai_endpoints.langfuse_endpoints import (
     router as langfuse_router,
 )
@@ -9128,7 +9128,7 @@ app.include_router(router)
 app.include_router(rerank_router)
 app.include_router(fine_tuning_router)
 app.include_router(vertex_router)
-app.include_router(gemini_router)
+app.include_router(llm_passthrough_router)
 app.include_router(langfuse_router)
 app.include_router(pass_through_router)
 app.include_router(health_router)
diff --git a/tests/proxy_admin_ui_tests/test_route_check_unit_tests.py b/tests/proxy_admin_ui_tests/test_route_check_unit_tests.py
index 001cc0640..a8bba211f 100644
--- a/tests/proxy_admin_ui_tests/test_route_check_unit_tests.py
+++ b/tests/proxy_admin_ui_tests/test_route_check_unit_tests.py
@@ -27,6 +27,9 @@ from fastapi import HTTPException, Request
 import pytest
 from litellm.proxy.auth.route_checks import RouteChecks
 from litellm.proxy._types import LiteLLM_UserTable, LitellmUserRoles, UserAPIKeyAuth
+from litellm.proxy.pass_through_endpoints.llm_passthrough_endpoints import (
+    router as llm_passthrough_router,
+)
 
 # Replace the actual hash_token function with our mock
 import litellm.proxy.auth.route_checks
@@ -56,12 +59,21 @@ def test_is_llm_api_route():
     assert RouteChecks.is_llm_api_route("/vertex-ai/text") is True
     assert RouteChecks.is_llm_api_route("/gemini/generate") is True
     assert RouteChecks.is_llm_api_route("/cohere/generate") is True
+    assert RouteChecks.is_llm_api_route("/anthropic/messages") is True
+    assert RouteChecks.is_llm_api_route("/anthropic/v1/messages") is True
+    assert RouteChecks.is_llm_api_route("/azure/endpoint") is True
 
     # check non-matching routes
     assert RouteChecks.is_llm_api_route("/some/random/route") is False
     assert RouteChecks.is_llm_api_route("/key/regenerate/82akk800000000jjsk") is False
     assert RouteChecks.is_llm_api_route("/key/82akk800000000jjsk/delete") is False
 
+    # check all routes in llm_passthrough_router, ensure they are considered llm api routes
+    for route in llm_passthrough_router.routes:
+        route_path = str(route.path)
+        print("route_path", route_path)
+        assert RouteChecks.is_llm_api_route(route_path) is True
+
 
 # Test _route_matches_pattern
 def test_route_matches_pattern():
diff --git a/tests/proxy_unit_tests/test_proxy_server.py b/tests/proxy_unit_tests/test_proxy_server.py
index b1c00ce75..d70962858 100644
--- a/tests/proxy_unit_tests/test_proxy_server.py
+++ b/tests/proxy_unit_tests/test_proxy_server.py
@@ -1794,7 +1794,7 @@ async def test_add_callback_via_key_litellm_pre_call_utils_langsmith(
 async def test_gemini_pass_through_endpoint():
     from starlette.datastructures import URL
 
-    from litellm.proxy.vertex_ai_endpoints.google_ai_studio_endpoints import (
+    from litellm.proxy.pass_through_endpoints.llm_passthrough_endpoints import (
         Request,
         Response,
         gemini_proxy_route,