diff --git a/.github/workflows/scheduled_test.yml b/.github/workflows/scheduled_test.yml
index 7ce59d5b695..5087c719347 100644
--- a/.github/workflows/scheduled_test.yml
+++ b/.github/workflows/scheduled_test.yml
@@ -34,12 +34,19 @@ jobs:
           working-directory: libs/langchain
           cache-key: scheduled
 
+      - name: 'Authenticate to Google Cloud'
+        id: 'auth'
+        uses: 'google-github-actions/auth@v1'
+        with:
+          credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
+
       - name: Install dependencies
         working-directory: libs/langchain
         shell: bash
         run: |
           echo "Running scheduled tests, installing dependencies with poetry..."
           poetry install --with=test_integration
+          poetry run pip install google-cloud-aiplatform
 
       - name: Run tests
         shell: bash
diff --git a/libs/langchain/tests/integration_tests/chat_models/test_vertexai.py b/libs/langchain/tests/integration_tests/chat_models/test_vertexai.py
index cc5163e5251..7a50f70a5cb 100644
--- a/libs/langchain/tests/integration_tests/chat_models/test_vertexai.py
+++ b/libs/langchain/tests/integration_tests/chat_models/test_vertexai.py
@@ -18,6 +18,14 @@ from langchain.schema import LLMResult
 from langchain.schema.messages import AIMessage, HumanMessage, SystemMessage
 
 
+@pytest.mark.parametrize("model_name", [None, "codechat-bison", "chat-bison"])
+def test_vertexai_instantiation(model_name: str) -> None:
+    model = ChatVertexAI(model_name=model_name)
+    assert model._llm_type == "vertexai"
+    assert model.model_name == model.client._model_id
+
+
+@pytest.mark.scheduled
 @pytest.mark.parametrize("model_name", [None, "codechat-bison", "chat-bison"])
 def test_vertexai_single_call(model_name: str) -> None:
     if model_name:
@@ -28,10 +36,9 @@ def test_vertexai_single_call(model_name: str) -> None:
     response = model([message])
     assert isinstance(response, AIMessage)
     assert isinstance(response.content, str)
-    assert model._llm_type == "vertexai"
-    assert model.model_name == model.client._model_id
 
 
+@pytest.mark.scheduled
 @pytest.mark.asyncio
 async def test_vertexai_agenerate() -> None:
     model = ChatVertexAI(temperature=0)
@@ -44,6 +51,7 @@ async def test_vertexai_agenerate() -> None:
     assert response.generations[0][0] == sync_response.generations[0][0]
 
 
+@pytest.mark.scheduled
 def test_vertexai_single_call_with_context() -> None:
     model = ChatVertexAI()
     raw_context = (
@@ -60,6 +68,7 @@ def test_vertexai_single_call_with_context() -> None:
     assert isinstance(response.content, str)
 
 
+@pytest.mark.scheduled
 def test_vertexai_single_call_with_examples() -> None:
     model = ChatVertexAI()
     raw_context = "My name is Ned. You are my personal assistant."
@@ -74,6 +83,7 @@ def test_vertexai_single_call_with_examples() -> None:
     assert isinstance(response.content, str)
 
 
+@pytest.mark.scheduled
 @pytest.mark.parametrize("model_name", [None, "codechat-bison", "chat-bison"])
 def test_vertexai_single_call_with_history(model_name: str) -> None:
     if model_name:
@@ -118,7 +128,7 @@ def test_parse_chat_history_correct() -> None:
     ]
 
 
-def test_vertexai_single_call_failes_no_message() -> None:
+def test_vertexai_single_call_fails_no_message() -> None:
     chat = ChatVertexAI()
     with pytest.raises(ValueError) as exc_info:
         _ = chat([])
diff --git a/libs/langchain/tests/integration_tests/llms/test_vertexai.py b/libs/langchain/tests/integration_tests/llms/test_vertexai.py
index 994f75a86d4..561e10a002c 100644
--- a/libs/langchain/tests/integration_tests/llms/test_vertexai.py
+++ b/libs/langchain/tests/integration_tests/llms/test_vertexai.py
@@ -15,20 +15,26 @@ from langchain.llms import VertexAI, VertexAIModelGarden
 from langchain.schema import LLMResult
 
 
-def test_vertex_call() -> None:
-    llm = VertexAI(temperature=0)
-    output = llm("Say foo:")
-    assert isinstance(output, str)
+def test_vertex_initialization() -> None:
+    llm = VertexAI()
     assert llm._llm_type == "vertexai"
     assert llm.model_name == llm.client._model_id
 
 
+def test_vertex_call() -> None:
+    llm = VertexAI(temperature=0)
+    output = llm("Say foo:")
+    assert isinstance(output, str)
+
+
+@pytest.mark.scheduled
 def test_vertex_generate() -> None:
     llm = VertexAI(temperate=0)
     output = llm.generate(["Please say foo:"])
     assert isinstance(output, LLMResult)
 
 
+@pytest.mark.scheduled
 @pytest.mark.asyncio
 async def test_vertex_agenerate() -> None:
     llm = VertexAI(temperate=0)
@@ -36,7 +42,8 @@ async def test_vertex_agenerate() -> None:
     assert isinstance(output, LLMResult)
 
 
-def test_vertext_stream() -> None:
+@pytest.mark.scheduled
+def test_vertex_stream() -> None:
     llm = VertexAI(temperate=0)
     outputs = list(llm.stream("Please say foo:"))
     assert isinstance(outputs[0], str)
@@ -63,7 +70,6 @@ def test_model_garden() -> None:
     project = os.environ["PROJECT"]
     llm = VertexAIModelGarden(endpoint_id=endpoint_id, project=project)
     output = llm("What is the meaning of life?")
-    print(output)
     assert isinstance(output, str)
     assert llm._llm_type == "vertexai_model_garden"