diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index fb80de3e77d..1c15f671eb0 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -51643,6 +51643,70 @@
         "litellm_provider": "vertex_ai",
         "mode": "vector_store"
     },
+    "vertex_ai/semantic-ranker-default": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-002": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-003": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
     "openai/container": {
         "code_interpreter_cost_per_session": 0.03,
         "litellm_provider": "openai",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index fb80de3e77d..1c15f671eb0 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -51643,6 +51643,70 @@
         "litellm_provider": "vertex_ai",
         "mode": "vector_store"
     },
+    "vertex_ai/semantic-ranker-default": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-002": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-003": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-default@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast-004": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
+    "vertex_ai/semantic-ranker-fast@latest": {
+        "input_cost_per_query": 0.001,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "vertex_ai",
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cloud.google.com/generative-ai-app-builder/pricing"
+    },
     "openai/container": {
         "code_interpreter_cost_per_session": 0.03,
         "litellm_provider": "openai",
diff --git a/tests/unit/test_cost_calculator.py b/tests/unit/test_cost_calculator.py
index 8dbef772472..92c55ff4fbb 100644
--- a/tests/unit/test_cost_calculator.py
+++ b/tests/unit/test_cost_calculator.py
@@ -1059,9 +1059,9 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero():
     router: Final = Router(
         model_list=[
             {
-                "model_name": "semantic-ranker-default-004",
+                "model_name": "semantic-ranker-custom-test",
                 "litellm_params": {
-                    "model": "vertex_ai/semantic-ranker-default-004",
+                    "model": "vertex_ai/semantic-ranker-custom-test",
                     "vertex_project": "test-project",
                     "vertex_location": "us-east5",
                 },
@@ -1070,7 +1070,7 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero():
         ]
     )
     router_model_id: Final = router.model_list[0]["model_info"]["id"]
-    assert litellm.model_cost["vertex_ai/semantic-ranker-default-004"].get("input_cost_per_query") is None
+    assert litellm.model_cost.get("vertex_ai/semantic-ranker-custom-test", {}).get("input_cost_per_query") is None
 
     response: Final = RerankResponse(
         id="vertex_ai_rerank_test",
@@ -1080,7 +1080,7 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero():
 
     cost: Final = completion_cost(
         completion_response=response,
-        model="vertex_ai/semantic-ranker-default-004",
+        model="vertex_ai/semantic-ranker-custom-test",
         custom_llm_provider="vertex_ai",
         call_type="arerank",
         custom_pricing=True,
@@ -1090,6 +1090,39 @@ def test_per_query_priced_rerank_deployment_completion_cost_is_nonzero():
     assert cost == pytest.approx(3 * 0.001)
 
 
+@pytest.mark.parametrize(
+    "model",
+    (
+        "vertex_ai/semantic-ranker-default",
+        "vertex_ai/semantic-ranker-default@latest",
+        "vertex_ai/semantic-ranker-default-004",
+        "vertex_ai/semantic-ranker-default-003",
+        "vertex_ai/semantic-ranker-default-002",
+        "vertex_ai/semantic-ranker-fast",
+        "vertex_ai/semantic-ranker-fast@latest",
+        "vertex_ai/semantic-ranker-fast-004",
+    ),
+)
+def test_vertex_semantic_ranker_rerank_completion_cost_is_nonzero(
+    model: str, _local_model_cost_map: None
+) -> None:
+    response: Final = RerankResponse(
+        id="vertex_ai_rerank_pricing_test",
+        results=[],
+        meta={"billed_units": {"search_units": 3}},
+    )
+
+    cost: Final = completion_cost(
+        completion_response=response,
+        model=model,
+        custom_llm_provider="vertex_ai",
+        call_type="rerank",
+    )
+
+    assert cost > 0
+    assert cost == pytest.approx(3 * litellm.model_cost[model]["input_cost_per_query"])
+
+
 def test_azure_realtime_cost_calculator(_local_model_cost_map):
 
     cost = handle_realtime_stream_cost_calculation(