diff --git a/test/collection/test_classes_generative.py b/test/collection/test_classes_generative.py
index 5d9496417..bcce1d160 100644
--- a/test/collection/test_classes_generative.py
+++ b/test/collection/test_classes_generative.py
@@ -275,6 +275,47 @@ def test_generative_parameters_images_parsing(
                 ),
             ),
         ),
+        (
+            GenerativeConfig.google_vertex(
+                api_endpoint="http://localhost:8080",
+                project_id="my-project",
+                endpoint_id="12345678901234567890123456789012",
+                region="us-west1",
+                frequency_penalty=0.5,
+                max_tokens=100,
+                model="text-to-image",
+                presence_penalty=0.5,
+                temperature=0.5,
+                top_k=50,
+                top_p=0.9,
+                stop_sequences=["\n"],
+                location="us-central1",
+            )._to_grpc(
+                _GenerativeConfigRuntimeOptions(
+                    return_metadata=True, images=[LOGO_ENCODED], image_properties=["image"]
+                )
+            ),
+            generative_pb2.GenerativeProvider(
+                return_metadata=True,
+                google=generative_pb2.GenerativeGoogle(
+                    api_endpoint="localhost:8080",
+                    endpoint_id="12345678901234567890123456789012",
+                    frequency_penalty=0.5,
+                    max_tokens=100,
+                    model="text-to-image",
+                    presence_penalty=0.5,
+                    project_id="my-project",
+                    region="us-west1",
+                    location="us-central1",
+                    stop_sequences=base_pb2.TextArray(values=["\n"]),
+                    temperature=0.5,
+                    top_k=50,
+                    top_p=0.9,
+                    images=base_pb2.TextArray(values=[LOGO_ENCODED]),
+                    image_properties=base_pb2.TextArray(values=["image"]),
+                ),
+            ),
+        ),
         (
             GenerativeConfig.mistral(
                 base_url="http://localhost:8080",
diff --git a/weaviate/collections/classes/generative.py b/weaviate/collections/classes/generative.py
index d5c1a5de2..f494661dd 100644
--- a/weaviate/collections/classes/generative.py
+++ b/weaviate/collections/classes/generative.py
@@ -423,6 +423,7 @@ class _GenerativeGoogle(_GenerativeConfigRuntime):
     presence_penalty: Optional[float]
     project_id: Optional[str]
     region: Optional[str]
+    location: Optional[str]
     stop_sequences: Optional[List[str]]
     temperature: Optional[float]
     top_k: Optional[int]
@@ -447,6 +448,7 @@ def _to_grpc(self, opts: _GenerativeConfigRuntimeOptions) -> generative_pb2.Gene
                 presence_penalty=self.presence_penalty,
                 project_id=self.project_id,
                 region=self.region,
+                location=self.location,
                 stop_sequences=_to_text_array(self.stop_sequences),
                 temperature=self.temperature,
                 top_k=self.top_k,
@@ -945,6 +947,7 @@ def google(
             presence_penalty=presence_penalty,
             project_id=project_id,
             region=region,
+            location=None,
             stop_sequences=stop_sequences,
             temperature=temperature,
             top_k=top_k,
@@ -966,6 +969,7 @@ def google_vertex(
         top_k: Optional[int] = None,
         top_p: Optional[float] = None,
         stop_sequences: Optional[List[str]] = None,
+        location: Optional[str] = None,
     ) -> _GenerativeConfigRuntime:
         """Create a `_GenerativeGoogle` object for use when performing AI generation using the `generative-google` module.
 
@@ -980,11 +984,17 @@ def google_vertex(
             model: The model ID to use. Defaults to `None`, which uses the server-defined default
             presence_penalty: The presence penalty to use. Defaults to `None`, which uses the server-defined default
             project_id: The project ID to use. Defaults to `None`, which uses the server-defined default
-            region: The region to use. Defaults to `None`, which uses the server-defined default
+            region: The region the Vertex AI endpoint is served from. For `gemini*` models this selects the API host
+                (`<region>-aiplatform.googleapis.com`); for the other models the host comes from `api_endpoint` instead.
+                Defaults to `None`, which uses the server-defined default
             stop_sequences: The stop sequences to use. Defaults to `None`, which uses the server-defined default
             temperature: The temperature to use. Defaults to `None`, which uses the server-defined default
             top_k: The top K to use. Defaults to `None`, which uses the server-defined default
             top_p: The top P to use. Defaults to `None`, which uses the server-defined default
+            location: The Vertex AI location, i.e. the `locations/<location>` segment of the request URL. This is
+                distinct from `region`: `region` picks the host, `location` picks the path. For `gemini*` models the
+                special value `"global"` selects the region-less `aiplatform.googleapis.com` host, so `region` is then
+                unused. Defaults to `None`, which uses the server-defined default of `us-central1`
         """
         return _GenerativeGoogle(
             api_endpoint=TypeAdapter(AnyHttpUrl).validate_python(api_endpoint)
@@ -997,6 +1007,7 @@ def google_vertex(
             presence_penalty=presence_penalty,
             project_id=project_id,
             region=region,
+            location=location,
             stop_sequences=stop_sequences,
             temperature=temperature,
             top_k=top_k,
@@ -1041,6 +1052,7 @@ def google_gemini(
             presence_penalty=presence_penalty,
             project_id=None,
             region=None,
+            location=None,
             stop_sequences=stop_sequences,
             temperature=temperature,
             top_k=top_k,