diff --git a/docs/my-website/docs/providers/vertex_self_deployed.md b/docs/my-website/docs/providers/vertex_self_deployed.md
index f7e7f181f58..98eff5d3682 100644
--- a/docs/my-website/docs/providers/vertex_self_deployed.md
+++ b/docs/my-website/docs/providers/vertex_self_deployed.md
@@ -135,7 +135,7 @@ Deploy Gemma models on custom Vertex AI prediction endpoints with OpenAI-compati
 model_list:
   - model_name: gemma-model
     litellm_params:
-      model: vertex_ai/gemma/gemma-3-12b-it-1759525599171
+      model: vertex_ai/gemma/gemma-3-12b-it-1222199011122
       api_base: https://ENDPOINT.us-central1-PROJECT.prediction.vertexai.goog/v1/projects/PROJECT_ID/locations/us-central1/endpoints/ENDPOINT_ID:predict
       vertex_project: "my-project-id"
       vertex_location: "us-central1"
@@ -168,7 +168,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
 from litellm import completion
 
 response = completion(
-    model="vertex_ai/gemma/gemma-3-12b-it-1759525599171",
+    model="vertex_ai/gemma/gemma-3-12b-it-1222199011122",
     messages=[{"role": "user", "content": "What is machine learning?"}],
     api_base="https://ENDPOINT.us-central1-PROJECT.prediction.vertexai.goog/v1/projects/PROJECT_ID/locations/us-central1/endpoints/ENDPOINT_ID:predict",
     vertex_project="my-project-id",
diff --git a/litellm/llms/vertex_ai/vertex_gemma_models/main.py b/litellm/llms/vertex_ai/vertex_gemma_models/main.py
index 2aa0bd24c0f..8203b285ebd 100644
--- a/litellm/llms/vertex_ai/vertex_gemma_models/main.py
+++ b/litellm/llms/vertex_ai/vertex_gemma_models/main.py
@@ -7,7 +7,7 @@ with @requestFormat: "chatCompletions" and returns responses wrapped in 'predict
 Usage:
 
 response = litellm.completion(
-    model="vertex_ai/gemma/gemma-3-12b-it-1759525599171",
+    model="vertex_ai/gemma/gemma-3-12b-it-1222199011122",
     messages=[{"role": "user", "content": "What is machine learning?"}],
     vertex_project="your-project-id",
     vertex_location="us-central1",
diff --git a/tests/test_litellm/llms/vertex_ai/vertex_gemma_models/test_vertex_gemma_transformation.py b/tests/test_litellm/llms/vertex_ai/vertex_gemma_models/test_vertex_gemma_transformation.py
index 2c1ce7a652c..1ff9009bb8f 100644
--- a/tests/test_litellm/llms/vertex_ai/vertex_gemma_models/test_vertex_gemma_transformation.py
+++ b/tests/test_litellm/llms/vertex_ai/vertex_gemma_models/test_vertex_gemma_transformation.py
@@ -42,8 +42,8 @@ class TestVertexGemmaCompletion:
         Expected Vertex Response:
         {
             "deployedModelId": "1207280419999999999",
-            "model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1759525599171",
-            "modelDisplayName": "gemma-3-12b-it-1759525599171",
+            "model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1222199011122",
+            "modelDisplayName": "gemma-3-12b-it-1222199011122",
             "modelVersionId": "1",
             "predictions": {
                 "choices": [
@@ -79,8 +79,8 @@ class TestVertexGemmaCompletion:
         # Real Vertex response from user's spec
         mock_vertex_response = {
             "deployedModelId": "1207280419999999999",
-            "model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1759525599171",
-            "modelDisplayName": "gemma-3-12b-it-1759525599171",
+            "model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1222199011122",
+            "modelDisplayName": "gemma-3-12b-it-1222199011122",
             "modelVersionId": "1",
             "predictions": {
                 "choices": [
@@ -122,7 +122,7 @@ class TestVertexGemmaCompletion:
             
             # Call litellm.acompletion()
             response = await litellm.acompletion(
-                model="vertex_ai/gemma/gemma-3-12b-it-1759525599171",
+                model="vertex_ai/gemma/gemma-3-12b-it-1222199011122",
                 messages=[{"role": "user", "content": "What is machine learning?"}],
                 max_tokens=100,
                 api_base="https://32277599999999999.us-central1-10582012152.prediction.vertexai.goog/v1/projects/PROJECT_ID/locations/us-central1/endpoints/ENDPOINT_ID:predict",
@@ -162,7 +162,7 @@ class TestVertexGemmaCompletion:
             assert response.object == "chat.completion"
             assert response.created == 1759863903
             # Model name has the gemma/ prefix stripped during processing
-            assert response.model == "gemma-3-12b-it-1759525599171"
+            assert response.model == "gemma-3-12b-it-1222199011122"
             
             # Validate choices
             assert len(response.choices) == 1