diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index f2b292c92..385dc2ead 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -1357,6 +1357,26 @@
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
+    "text-embedding-004": {
+        "max_tokens": 3072,
+        "max_input_tokens": 3072,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
+    "text-multilingual-embedding-002": {
+        "max_tokens": 2048,
+        "max_input_tokens": 2048,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
     "textembedding-gecko": {
         "max_tokens": 3072,
         "max_input_tokens": 3072,
diff --git a/litellm/tests/test_amazing_vertex_completion.py b/litellm/tests/test_amazing_vertex_completion.py
index ce2e3dcdb..84d3a2bfc 100644
--- a/litellm/tests/test_amazing_vertex_completion.py
+++ b/litellm/tests/test_amazing_vertex_completion.py
@@ -810,6 +810,21 @@ def test_vertexai_embedding():
         pytest.fail(f"Error occurred: {e}")
 
 
+def test_vertexai_embedding_embedding_latest():
+    try:
+        load_vertex_ai_credentials()
+        litellm.set_verbose = True
+        response = embedding(
+            model="vertex_ai/text-embedding-004",
+            input=["good morning from litellm", "this is another item"],
+        )
+        print(f"response:", response)
+    except litellm.RateLimitError as e:
+        pass
+    except Exception as e:
+        pytest.fail(f"Error occurred: {e}")
+
+
 @pytest.mark.asyncio
 async def test_vertexai_aembedding():
     try:
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index f2b292c92..385dc2ead 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -1357,6 +1357,26 @@
         "mode": "image_generation",
         "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
     },
+    "text-embedding-004": {
+        "max_tokens": 3072,
+        "max_input_tokens": 3072,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
+    "text-multilingual-embedding-002": {
+        "max_tokens": 2048,
+        "max_input_tokens": 2048,
+        "output_vector_size": 768,
+        "input_cost_per_token": 0.00000000625,
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "mode": "embedding",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
+    },
     "textembedding-gecko": {
         "max_tokens": 3072,
         "max_input_tokens": 3072,