fix(proxy): extract model from vertex ai passthrough url pattern

Author: krisxia0506

litellm/llms/vertex_ai/common_utils.py

@@ -733,6 +733,16 @@ def get_vertex_location_from_url(url: str) -> Optional[str]:
     return match.group(1) if match else None
 
 
+def get_vertex_model_id_from_url(url: str) -> Optional[str]:
+    """
+    Get the vertex model id from the url
+
+    `https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:streamGenerateContent`
+    """
+    match = re.search(r"/models/([^/:]+)", url)
+    return match.group(1) if match else None
+
+
 def replace_project_and_location_in_route(
     requested_route: str, vertex_project: str, vertex_location: str
 ) -> str:
@@ -782,6 +792,15 @@ def construct_target_url(
     if "cachedContent" in requested_route:
         vertex_version = "v1beta1"
 
+    # Check if the requested route starts with a version
+    # e.g. /v1beta1/publishers/google/models/gemini-3-pro-preview:streamGenerateContent
+    if requested_route.startswith("/v1/"):
+        vertex_version = "v1"
+        requested_route = requested_route.replace("/v1/", "/", 1)
+    elif requested_route.startswith("/v1beta1/"):
+        vertex_version = "v1beta1"
+        requested_route = requested_route.replace("/v1beta1/", "/", 1)
+
     base_requested_route = "{}/projects/{}/locations/{}".format(
         vertex_version, vertex_project, vertex_location
     )

litellm/proxy/auth/auth_utils.py

@@ -616,6 +616,14 @@ def get_model_from_request(
         if match:
             model = match.group(1)
 
+    # If still not found, extract from Vertex AI passthrough route
+    # Pattern: /vertex_ai/.../models/{model_id}:*
+    # Example: /vertex_ai/v1/.../models/gemini-1.5-pro:generateContent
+    if model is None and "/vertex" in route.lower():
+        vertex_match = re.search(r"/models/([^/:]+)", route)
+        if vertex_match:
+            model = vertex_match.group(1)
+
     return model
 
 

litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py

@@ -1547,6 +1547,7 @@ async def _base_vertex_proxy_route(
     from litellm.llms.vertex_ai.common_utils import (
         construct_target_url,
         get_vertex_location_from_url,
+        get_vertex_model_id_from_url,
         get_vertex_project_id_from_url,
     )
 
@@ -1576,6 +1577,25 @@ async def _base_vertex_proxy_route(
         vertex_location=vertex_location,
     )
 
+    if vertex_project is None or vertex_location is None:
+        # Check if model is in router config
+        model_id = get_vertex_model_id_from_url(endpoint)
+        if model_id:
+            from litellm.proxy.proxy_server import llm_router
+
+            if llm_router:
+                try:
+                    # Use the dedicated pass-through deployment selection method to automatically filter use_in_pass_through=True
+                    deployment = llm_router.get_available_deployment_for_pass_through(model=model_id)
+                    if deployment:
+                        litellm_params = deployment.get("litellm_params", {})
+                        vertex_project = litellm_params.get("vertex_project")
+                        vertex_location = litellm_params.get("vertex_location")
+                except Exception as e:
+                    verbose_proxy_logger.debug(
+                        f"Error getting available deployment for model {model_id}: {e}"
+                    )
+
     vertex_credentials = passthrough_endpoint_router.get_vertex_credentials(
         project_id=vertex_project,
         location=vertex_location,