diff --git a/litellm/proxy/example_config_yaml/store_model_db_config.yaml b/litellm/proxy/example_config_yaml/store_model_db_config.yaml
index 91dee9f9073..b9cd2302046 100644
--- a/litellm/proxy/example_config_yaml/store_model_db_config.yaml
+++ b/litellm/proxy/example_config_yaml/store_model_db_config.yaml
@@ -3,7 +3,7 @@ model_list:
     litellm_params:
       model: openai/my-fake-model
       api_key: my-fake-key
-      api_base: http://host.docker.internal:8090/
+      api_base: https://exampleopenaiendpoint-production.up.railway.app/
 
 general_settings:
   store_model_in_db: true
diff --git a/tests/llm_translation/test_triton.py b/tests/llm_translation/test_triton.py
index 7327be73524..2d1ca39e1dc 100644
--- a/tests/llm_translation/test_triton.py
+++ b/tests/llm_translation/test_triton.py
@@ -360,7 +360,7 @@ async def test_triton_embeddings():
         litellm.set_verbose = True
         response = await litellm.aembedding(
             model="triton/my-triton-model",
-            api_base="http://127.0.0.1:8090/triton/embeddings",
+            api_base="https://exampleopenaiendpoint-production.up.railway.app/triton/embeddings",
             input=["good morning from litellm"],
         )
         print(f"response: {response}")
diff --git a/tests/load_tests/test_vertex_embeddings_load_test.py b/tests/load_tests/test_vertex_embeddings_load_test.py
index 83060ec94bc..9beee710553 100644
--- a/tests/load_tests/test_vertex_embeddings_load_test.py
+++ b/tests/load_tests/test_vertex_embeddings_load_test.py
@@ -59,7 +59,7 @@ def load_vertex_ai_credentials():
 
 async def create_async_vertex_embedding_task():
     load_vertex_ai_credentials()
-    base_url = "http://127.0.0.1:8090/v1/projects/pathrise-convert-1606954137718/locations/us-central1/publishers/google/models/textembedding-gecko@001"
+    base_url = "https://exampleopenaiendpoint-production.up.railway.app/v1/projects/pathrise-convert-1606954137718/locations/us-central1/publishers/google/models/textembedding-gecko@001"
     embedding_args = {
         "model": "vertex_ai/textembedding-gecko",
         "input": "This is a test sentence for embedding.",
diff --git a/tests/load_tests/test_vertex_load_tests.py b/tests/load_tests/test_vertex_load_tests.py
index b967bb00ada..9130873b970 100644
--- a/tests/load_tests/test_vertex_load_tests.py
+++ b/tests/load_tests/test_vertex_load_tests.py
@@ -118,7 +118,7 @@ async def make_async_calls(message_type="text"):
 
 
 def create_async_task(message_type):
-    base_url = "http://127.0.0.1:8090/v1/projects/pathrise-convert-1606954137718/locations/us-central1/publishers/google/models/gemini-1.0-pro-vision-001"
+    base_url = "https://exampleopenaiendpoint-production.up.railway.app/v1/projects/pathrise-convert-1606954137718/locations/us-central1/publishers/google/models/gemini-1.0-pro-vision-001"
 
     if message_type == "text":
         messages = [{"role": "user", "content": "hi"}]
diff --git a/tests/store_model_in_db_tests/test_callbacks_in_db.py b/tests/store_model_in_db_tests/test_callbacks_in_db.py
index 4ddefaff4e1..4a851251a3e 100644
--- a/tests/store_model_in_db_tests/test_callbacks_in_db.py
+++ b/tests/store_model_in_db_tests/test_callbacks_in_db.py
@@ -21,7 +21,7 @@ from openai.types.chat import ChatCompletion
 load_dotenv()
 
 # used for testing
-LANGFUSE_BASE_URL = "http://127.0.0.1:8090/slow"
+LANGFUSE_BASE_URL = "https://exampleopenaiendpoint-production-c715.up.railway.app"
 
 
 async def config_update(session, routing_strategy=None):