diff --git a/litellm/__init__.py b/litellm/__init__.py
index 6f27e2881a..5ff730464a 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -61,13 +61,14 @@ from litellm.constants import (
     DEFAULT_ALLOWED_FAILS,
 )
 from litellm.types.guardrails import GuardrailItem
-from litellm_proxy._types import (
+from litellm.types.proxy.management_endpoints.ui_sso import DefaultTeamSSOParams
+from litellm.types.utils import (
+    StandardKeyGenerationConfig,
+    LlmProviders,
     KeyManagementSystem,
     KeyManagementSettings,
     LiteLLM_UpperboundKeyGenerateParams,
 )
-from litellm.types.proxy.management_endpoints.ui_sso import DefaultTeamSSOParams
-from litellm.types.utils import StandardKeyGenerationConfig, LlmProviders
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.litellm_core_utils.logging_callback_manager import LoggingCallbackManager
 import httpx
diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index fa03c59270..526a097606 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -2276,3 +2276,48 @@ class KeyManagementSystem(enum.Enum):
     HASHICORP_VAULT = "hashicorp_vault"
     LOCAL = "local"
     AWS_KMS = "aws_kms"
+
+
+class KeyManagementSettings(LiteLLMPydanticObjectBase):
+    hosted_keys: Optional[List] = None
+    store_virtual_keys: Optional[bool] = False
+    """
+    If True, virtual keys created by litellm will be stored in the secret manager
+    """
+    prefix_for_stored_virtual_keys: str = "litellm/"
+    """
+    If set, this prefix will be used for stored virtual keys in the secret manager
+    """
+
+    access_mode: Literal["read_only", "write_only", "read_and_write"] = "read_only"
+    """
+    Access mode for the secret manager, when write_only will only use for writing secrets
+    """
+
+    primary_secret_name: Optional[str] = None
+    """
+    If set, will read secrets from this primary secret in the secret manager
+
+    eg. on AWS you can store multiple secret values as K/V pairs in a single secret
+    """
+
+
+class LiteLLM_UpperboundKeyGenerateParams(LiteLLMPydanticObjectBase):
+    """
+    Set default upperbound to max budget a key called via `/key/generate` can be.
+
+    Args:
+        max_budget (Optional[float], optional): Max budget a key can be. Defaults to None.
+        budget_duration (Optional[str], optional): Duration of the budget. Defaults to None.
+        duration (Optional[str], optional): Duration of the key. Defaults to None.
+        max_parallel_requests (Optional[int], optional): Max number of requests that can be made in parallel. Defaults to None.
+        tpm_limit (Optional[int], optional): Tpm limit. Defaults to None.
+        rpm_limit (Optional[int], optional): Rpm limit. Defaults to None.
+    """
+
+    max_budget: Optional[float] = None
+    budget_duration: Optional[str] = None
+    duration: Optional[str] = None
+    max_parallel_requests: Optional[int] = None
+    tpm_limit: Optional[int] = None
+    rpm_limit: Optional[int] = None
diff --git a/litellm_proxy/_types.py b/litellm_proxy/_types.py
index caa3d28716..702dd1969f 100644
--- a/litellm_proxy/_types.py
+++ b/litellm_proxy/_types.py
@@ -173,27 +173,6 @@ def hash_token(token: str):
     return hashed_token
 
 
-class LiteLLM_UpperboundKeyGenerateParams(LiteLLMPydanticObjectBase):
-    """
-    Set default upperbound to max budget a key called via `/key/generate` can be.
-
-    Args:
-        max_budget (Optional[float], optional): Max budget a key can be. Defaults to None.
-        budget_duration (Optional[str], optional): Duration of the budget. Defaults to None.
-        duration (Optional[str], optional): Duration of the key. Defaults to None.
-        max_parallel_requests (Optional[int], optional): Max number of requests that can be made in parallel. Defaults to None.
-        tpm_limit (Optional[int], optional): Tpm limit. Defaults to None.
-        rpm_limit (Optional[int], optional): Rpm limit. Defaults to None.
-    """
-
-    max_budget: Optional[float] = None
-    budget_duration: Optional[str] = None
-    duration: Optional[str] = None
-    max_parallel_requests: Optional[int] = None
-    tpm_limit: Optional[int] = None
-    rpm_limit: Optional[int] = None
-
-
 class KeyManagementRoutes(str, enum.Enum):
     """
     Enum for key management routes
@@ -1237,30 +1216,6 @@ class OrganizationRequest(LiteLLMPydanticObjectBase):
 class DeleteOrganizationRequest(LiteLLMPydanticObjectBase):
     organization_ids: List[str]  # required
 
-class KeyManagementSettings(LiteLLMPydanticObjectBase):
-    hosted_keys: Optional[List] = None
-    store_virtual_keys: Optional[bool] = False
-    """
-    If True, virtual keys created by litellm will be stored in the secret manager
-    """
-    prefix_for_stored_virtual_keys: str = "litellm/"
-    """
-    If set, this prefix will be used for stored virtual keys in the secret manager
-    """
-
-    access_mode: Literal["read_only", "write_only", "read_and_write"] = "read_only"
-    """
-    Access mode for the secret manager, when write_only will only use for writing secrets
-    """
-
-    primary_secret_name: Optional[str] = None
-    """
-    If set, will read secrets from this primary secret in the secret manager
-
-    eg. on AWS you can store multiple secret values as K/V pairs in a single secret
-    """
-
-
 class TeamDefaultSettings(LiteLLMPydanticObjectBase):
     team_id: str
 
diff --git a/litellm_proxy/proxy_server.py b/litellm_proxy/proxy_server.py
index 166b9a17df..63bc0ad653 100644
--- a/litellm_proxy/proxy_server.py
+++ b/litellm_proxy/proxy_server.py
@@ -33,6 +33,7 @@ from litellm.types.utils import (
     ModelResponse,
     ModelResponseStream,
     TextCompletionResponse,
+    KeyManagementSettings,
 )
 
 if TYPE_CHECKING: