diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py
index d39f12f05e2..4de2fd1299d 100644
--- a/litellm/proxy/_types.py
+++ b/litellm/proxy/_types.py
@@ -731,12 +731,7 @@ class GenerateRequestBase(LiteLLMPydanticObjectBase):
     metadata: Optional[dict] = {}
     tpm_limit: Optional[int] = None
     rpm_limit: Optional[int] = None
-    rpm_limit_type: Optional[
-        Literal["guaranteed_throughput", "best_effort_throughput"]
-    ] = None  # raise an error if 'guaranteed_throughput' is set and we're overallocating rpm
-    tpm_limit_type: Optional[
-        Literal["guaranteed_throughput", "best_effort_throughput"]
-    ] = None  # raise an error if 'guaranteed_throughput' is set and we're overallocating tpm
+
     budget_duration: Optional[str] = None
     allowed_cache_controls: Optional[list] = []
     config: Optional[dict] = {}
@@ -761,6 +756,12 @@ class KeyRequestBase(GenerateRequestBase):
     tags: Optional[List[str]] = None
     enforced_params: Optional[List[str]] = None
     allowed_routes: Optional[list] = []
+    rpm_limit_type: Optional[
+        Literal["guaranteed_throughput", "best_effort_throughput"]
+    ] = None  # raise an error if 'guaranteed_throughput' is set and we're overallocating rpm
+    tpm_limit_type: Optional[
+        Literal["guaranteed_throughput", "best_effort_throughput"]
+    ] = None  # raise an error if 'guaranteed_throughput' is set and we're overallocating tpm
 
 
 class LiteLLMKeyType(str, enum.Enum):