diff --git a/llama_stack/apis/models/models.py b/llama_stack/apis/models/models.py
index bebd90bc1..5258063da 100644
--- a/llama_stack/apis/models/models.py
+++ b/llama_stack/apis/models/models.py
@@ -59,8 +59,3 @@ class Models(Protocol):
 
     @webmethod(route="/models/get", method="POST")
     async def get_model(self, model_id: str) -> ModelsGetResponse: ...
-
-    @webmethod(route="/models/register")
-    async def register_model(
-        self, model_id: str, api: str, provider_spec: Dict[str, str]
-    ) -> ModelsRegisterResponse: ...
diff --git a/llama_stack/providers/impls/meta_reference/models/models.py b/llama_stack/providers/impls/meta_reference/models/models.py
index a7843f0fc..c3a2048c0 100644
--- a/llama_stack/providers/impls/meta_reference/models/models.py
+++ b/llama_stack/providers/impls/meta_reference/models/models.py
@@ -39,6 +39,8 @@ class MetaReferenceModelsImpl(Models):
         self.safety_api = safety_api
 
         self.models_list = []
+        model = get_model_id_from_api(self.inference_api)
+
         # TODO, make the inference route provider and use router provider to do the lookup dynamically
         if isinstance(
             self.inference_api,