diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py
index 9b373d8add5..4cb16b83a8e 100644
--- a/litellm/proxy/_types.py
+++ b/litellm/proxy/_types.py
@@ -2433,16 +2433,6 @@ class ConfigGeneralSettings(LiteLLMPydanticObjectBase):
             "is active as a reminder that hard enforcement is relaxed."
         ),
     )
-    skip_user_budget_on_team_key: bool | None = Field(
-        None,
-        description=(
-            "If True, restores the legacy behavior where a user's personal "
-            "max_budget is NOT enforced when their key belongs to a team; only "
-            "the team (and team-member) budgets apply. Defaults to False, meaning "
-            "the user's personal max_budget is always enforced regardless of "
-            "whether the key belongs to a team (see GitHub issue #12905)."
-        ),
-    )
     user_url_validation: Optional[bool] = Field(
         None,
         description=(
diff --git a/litellm/proxy/auth/auth_checks.py b/litellm/proxy/auth/auth_checks.py
index 6ed283d898b..24370a11c24 100644
--- a/litellm/proxy/auth/auth_checks.py
+++ b/litellm/proxy/auth/auth_checks.py
@@ -631,31 +631,28 @@ async def common_checks(
             )
 
         async def _user_max_budget_check() -> None:
-            if user_object is None or user_object.max_budget is None:
-                return
-            skip_for_team = (
-                general_settings.get("skip_user_budget_on_team_key") is True
-                and team_object is not None
-                and team_object.team_id is not None
-            )
-            if skip_for_team:
-                return
-            from litellm.proxy.proxy_server import get_current_spend
+            # 4.1 personal budget, if personal key
+            if (
+                (team_object is None or team_object.team_id is None)
+                and user_object is not None
+                and user_object.max_budget is not None
+            ):
+                from litellm.proxy.proxy_server import get_current_spend
 
-            user_budget = user_object.max_budget
-            user_spend = await get_current_spend(
-                counter_key=f"spend:user:{user_object.user_id}",
-                fallback_spend=user_object.spend or 0.0,
-                max_budget=user_budget,
-            )
-            if math.isfinite(user_budget) and user_spend >= user_budget:
-                raise litellm.BudgetExceededError(
-                    current_cost=user_spend,
+                user_budget = user_object.max_budget
+                user_spend = await get_current_spend(
+                    counter_key=f"spend:user:{user_object.user_id}",
+                    fallback_spend=user_object.spend or 0.0,
                     max_budget=user_budget,
-                    message=f"ExceededBudget: User={user_object.user_id} over budget. Spend={user_spend}, Budget={user_budget}",
-                    entity_type=Litellm_EntityType.USER.value,
-                    entity_id=user_object.user_id,
                 )
+                if math.isfinite(user_budget) and user_spend >= user_budget:
+                    raise litellm.BudgetExceededError(
+                        current_cost=user_spend,
+                        max_budget=user_budget,
+                        message=f"ExceededBudget: User={user_object.user_id} over budget. Spend={user_spend}, Budget={user_budget}",
+                        entity_type=Litellm_EntityType.USER.value,
+                        entity_id=user_object.user_id,
+                    )
 
         # Each scope reads a distinct counter key with no cross-scope ordering
         # dependency, so the per-scope Redis-first reads run concurrently instead
diff --git a/litellm/proxy/auth/user_api_key_auth.py b/litellm/proxy/auth/user_api_key_auth.py
index d63a8fda610..e856d0935bf 100644
--- a/litellm/proxy/auth/user_api_key_auth.py
+++ b/litellm/proxy/auth/user_api_key_auth.py
@@ -2439,7 +2439,6 @@ async def _reserve_budget_after_common_checks(
         proxy_logging_obj=proxy_logging_obj,
         end_user_id=end_user_id,
         end_user_object=end_user_object,
-        skip_user_budget_on_team_key=general_settings.get("skip_user_budget_on_team_key") is True,
     )
 
 
diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index ff54a4532c4..539e98cefb1 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -15016,7 +15016,6 @@ async def get_config_list(
         "forward_client_headers_to_llm_api": {"type": "Boolean"},
         "mcp_required_fields": {"type": "List"},
         "cancel_on_disconnect": {"type": "Boolean"},
-        "skip_user_budget_on_team_key": {"type": "Boolean"},
         "disable_auto_add_proxy_admin_to_teams": {"type": "Boolean"},
     }
 
diff --git a/litellm/proxy/spend_tracking/budget_reservation.py b/litellm/proxy/spend_tracking/budget_reservation.py
index 80fd8a1594e..d7d8303f706 100644
--- a/litellm/proxy/spend_tracking/budget_reservation.py
+++ b/litellm/proxy/spend_tracking/budget_reservation.py
@@ -137,7 +137,6 @@ async def reserve_budget_for_request(
     proxy_logging_obj: ProxyLogging,
     end_user_id: Optional[str] = None,
     end_user_object: Optional[Any] = None,
-    skip_user_budget_on_team_key: bool = False,
 ) -> Optional[dict]:
     if valid_token is None or not RouteChecks.is_llm_api_route(route=route):
         return None
@@ -156,7 +155,6 @@ async def reserve_budget_for_request(
         proxy_logging_obj=proxy_logging_obj,
         end_user_id=end_user_id,
         end_user_object=end_user_object,
-        skip_user_budget_on_team_key=skip_user_budget_on_team_key,
     )
     if not counters:
         return None
@@ -312,7 +310,6 @@ async def _get_budget_counters(
     proxy_logging_obj: ProxyLogging,
     end_user_id: Optional[str] = None,
     end_user_object: Optional[Any] = None,
-    skip_user_budget_on_team_key: bool = False,
 ) -> List[_BudgetCounter]:
     counters: List[_BudgetCounter] = []
 
@@ -361,9 +358,8 @@ async def _get_budget_counters(
             )
         )
 
-    is_team_key = team_object is not None and team_object.team_id is not None
     if (
-        not (is_team_key and skip_user_budget_on_team_key)
+        (team_object is None or team_object.team_id is None)
         and user_object is not None
         and user_object.user_id is not None
         and user_object.max_budget is not None
diff --git a/pyproject.toml b/pyproject.toml
index c784c1dd76a..e03a61df692 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "litellm"
-version = "1.94.0"
+version = "1.94.1"
 description = "Library to easily interface with LLM API providers"
 readme = "README.md"
 requires-python = ">=3.10, <3.15"
@@ -289,7 +289,7 @@ members = ["enterprise", "litellm-proxy-extras"]
 profile = "black"
 
 [tool.commitizen]
-version = "1.94.0"
+version = "1.94.1"
 version_files = [
     "pyproject.toml:^version",
 ]
diff --git a/tests/proxy_unit_tests/test_user_api_key_auth.py b/tests/proxy_unit_tests/test_user_api_key_auth.py
index 5471d2668e4..b01c15511a0 100644
--- a/tests/proxy_unit_tests/test_user_api_key_auth.py
+++ b/tests/proxy_unit_tests/test_user_api_key_auth.py
@@ -219,8 +219,8 @@ async def test_aaauser_personal_budgets(key_ownership):
     """
     Set a personal budget on a user
 
-    User budget is enforced regardless of key ownership (personal or team).
-    Both cases should raise BudgetExceededError when the user is over budget.
+    - have it only apply when key belongs to user -> raises BudgetExceededError
+    - if key belongs to team, have key respect team budget -> allows call to go through
     """
     import asyncio
     import time
@@ -278,9 +278,12 @@ async def test_aaauser_personal_budgets(key_ownership):
         == valid_token
     )
 
-    with pytest.raises(ProxyException) as exc_info:
+    if key_ownership == "user_key":
+        with pytest.raises(ProxyException) as exc_info:
+            await user_api_key_auth(request=request, api_key="Bearer " + user_key)
+        assert exc_info.value.type == ProxyErrorTypes.budget_exceeded
+    else:
         await user_api_key_auth(request=request, api_key="Bearer " + user_key)
-    assert exc_info.value.type == ProxyErrorTypes.budget_exceeded
 
 
 @pytest.mark.asyncio
diff --git a/tests/test_litellm/proxy/auth/test_auth_checks.py b/tests/test_litellm/proxy/auth/test_auth_checks.py
index 2da645bf4e1..10578bef395 100644
--- a/tests/test_litellm/proxy/auth/test_auth_checks.py
+++ b/tests/test_litellm/proxy/auth/test_auth_checks.py
@@ -4583,66 +4583,26 @@ async def test_common_checks_personal_user_budget_blocks_in_gather():
 
 
 @pytest.mark.asyncio
-async def test_user_budget_enforced_on_team_key():
-    """User budget must be enforced even when the key belongs to a team.
+async def test_common_checks_personal_user_budget_skipped_for_team_key():
+    """A user's personal max_budget does not apply to a team-scoped key.
 
-    Previously _user_max_budget_check skipped enforcement for team keys,
-    letting a user with a $100 personal budget spend unlimited through a
-    team key. This regression test ensures that is no longer the case.
+    Team keys are governed by the team (and team-member) budgets only; the key
+    owner's personal budget is deliberately out of scope. This asserts the read
+    path lets a team key through even when the user is far over their personal
+    budget, and fails if personal enforcement is reintroduced for team keys.
     """
     from fastapi import Request
 
     from litellm.proxy.auth.auth_checks import common_checks
 
     user = LiteLLM_UserTable(user_id="u1", spend=0.0, max_budget=100.0)
-    team = LiteLLM_TeamTable(team_id="t1", max_budget=2100.0)
+    team = LiteLLM_TeamTable(team_id="t1", spend=0.0, max_budget=1000.0)
     token = UserAPIKeyAuth(token="k1", user_id="u1", team_id="t1")
 
     async def _spend_by_counter(counter_key, fallback_spend, max_budget=None, **kwargs):
         return 999.0 if counter_key == "spend:user:u1" else 0.0
 
-    async def _no_membership(*a, **kw):
-        return None
-
-    with patch("litellm.proxy.proxy_server.prisma_client", None), patch(
-        "litellm.proxy.proxy_server.get_current_spend", _spend_by_counter
-    ), patch("litellm.proxy.auth.auth_checks.get_team_membership", _no_membership):
-        with pytest.raises(litellm.BudgetExceededError) as over:
-            await common_checks(
-                request_body={"messages": [{"role": "user", "content": "hi"}]},
-                team_object=team,
-                user_object=user,
-                end_user_object=None,
-                global_proxy_spend=None,
-                general_settings={},
-                route="/chat/completions",
-                llm_router=None,
-                proxy_logging_obj=MagicMock(),
-                valid_token=token,
-                request=MagicMock(spec=Request),
-            )
-    assert "User=u1" in str(over.value)
-
-
-@pytest.mark.asyncio
-async def test_skip_user_budget_on_team_key_flag_restores_old_behavior():
-    """Setting skip_user_budget_on_team_key=True skips user budget for team keys.
-
-    This is the opt-in escape hatch that restores the legacy behavior where
-    user budgets were not enforced when the key belonged to a team.
-    """
-    from fastapi import Request
-
-    from litellm.proxy.auth.auth_checks import common_checks
-
-    user = LiteLLM_UserTable(user_id="u1", spend=0.0, max_budget=100.0)
-    team = LiteLLM_TeamTable(team_id="t1", max_budget=2100.0)
-    token = UserAPIKeyAuth(token="k1", user_id="u1", team_id="t1")
-
-    async def _spend_by_counter(counter_key, fallback_spend, max_budget=None, **kwargs):
-        return 999.0 if counter_key == "spend:user:u1" else 0.0
-
-    async def _no_membership(*a, **kw):
+    async def _no_membership(*args, **kwargs):
         return None
 
     with patch("litellm.proxy.proxy_server.prisma_client", None), patch(
@@ -4654,7 +4614,7 @@ async def test_skip_user_budget_on_team_key_flag_restores_old_behavior():
             user_object=user,
             end_user_object=None,
             global_proxy_spend=None,
-            general_settings={"skip_user_budget_on_team_key": True},
+            general_settings={},
             route="/chat/completions",
             llm_router=None,
             proxy_logging_obj=MagicMock(),
diff --git a/tests/test_litellm/proxy/test_budget_reservation.py b/tests/test_litellm/proxy/test_budget_reservation.py
index 1db76aed61d..fb7a6b8c2d6 100644
--- a/tests/test_litellm/proxy/test_budget_reservation.py
+++ b/tests/test_litellm/proxy/test_budget_reservation.py
@@ -610,12 +610,12 @@ async def test_should_reserve_team_member_and_org_budget_counters(spend_counter_
 
 
 @pytest.mark.asyncio
-async def test_should_reserve_user_budget_counter_for_team_key(spend_counter_state):
-    """A user's personal budget must be reserved even when the key belongs to a team.
+async def test_should_not_reserve_user_budget_counter_for_team_key(spend_counter_state):
+    """The reservation path mirrors the read path: no personal user counter for a team key.
 
-    Regression for GitHub issue #12905: previously the reservation path skipped the
-    user spend counter whenever the key had a team, so a team key could overshoot the
-    user's personal max_budget under concurrency.
+    A team-scoped key reserves against the key and team counters only, so the key
+    owner's personal max_budget never gates a team request. Fails if the user
+    counter is reserved for team keys again.
     """
     counter_cache, key_cache = spend_counter_state
     proxy_logging_obj = ProxyLogging(user_api_key_cache=key_cache)
@@ -644,44 +644,7 @@ async def test_should_reserve_user_budget_counter_for_team_key(spend_counter_sta
             proxy_logging_obj=proxy_logging_obj,
         )
 
-    assert counter_cache.in_memory_cache.get_cache(key="spend:user:user-on-team") == pytest.approx(0.3)
-
-    await release_budget_reservation(reservation)
-
-
-@pytest.mark.asyncio
-async def test_should_skip_user_budget_counter_for_team_key_when_flag_set(spend_counter_state):
-    """skip_user_budget_on_team_key=True restores the legacy behavior where a user's
-    personal budget is not reserved for a team key."""
-    counter_cache, key_cache = spend_counter_state
-    proxy_logging_obj = ProxyLogging(user_api_key_cache=key_cache)
-    valid_token = UserAPIKeyAuth(
-        token="key-user-on-team-skip",
-        spend=0.0,
-        user_id="user-on-team-skip",
-        team_id="team-no-budget-skip",
-    )
-    team_object = LiteLLM_TeamTable(team_id="team-no-budget-skip", spend=0.0, max_budget=None)
-    user_object = LiteLLM_UserTable(user_id="user-on-team-skip", spend=0.0, max_budget=5.0)
-
-    with patch(
-        "litellm.proxy.spend_tracking.budget_reservation.estimate_request_max_cost",
-        return_value=0.3,
-    ):
-        reservation = await reserve_budget_for_request(
-            request_body=_request_body(),
-            route="/chat/completions",
-            llm_router=None,
-            valid_token=valid_token,
-            team_object=team_object,
-            user_object=user_object,
-            prisma_client=None,
-            user_api_key_cache=key_cache,
-            proxy_logging_obj=proxy_logging_obj,
-            skip_user_budget_on_team_key=True,
-        )
-
-    assert counter_cache.in_memory_cache.get_cache(key="spend:user:user-on-team-skip") is None
+    assert counter_cache.in_memory_cache.get_cache(key="spend:user:user-on-team") is None
 
     await release_budget_reservation(reservation)
 
diff --git a/tests/test_litellm/proxy/test_proxy_server.py b/tests/test_litellm/proxy/test_proxy_server.py
index a100e7837f4..a4a9a83d323 100644
--- a/tests/test_litellm/proxy/test_proxy_server.py
+++ b/tests/test_litellm/proxy/test_proxy_server.py
@@ -8875,38 +8875,6 @@ def test_get_config_list_includes_cancel_on_disconnect(monkeypatch):
         app.dependency_overrides.clear()
 
 
-def test_get_config_list_includes_skip_user_budget_on_team_key(monkeypatch):
-    """Related to #12905: the opt-out flag must be discoverable via /config/list so
-    it renders as a Boolean toggle on the Admin UI General Settings table. This
-    requires both the ConfigGeneralSettings field and the allowed_args entry."""
-    import types
-    from unittest.mock import AsyncMock, MagicMock
-
-    from fastapi.testclient import TestClient
-
-    import litellm.proxy.proxy_server as ps
-    from litellm.proxy._types import LitellmUserRoles, UserAPIKeyAuth
-    from litellm.proxy.proxy_server import app
-
-    mock_prisma = MagicMock()
-    mock_config_table = MagicMock()
-    mock_config_table.find_first = AsyncMock(return_value=None)
-    mock_prisma.db = types.SimpleNamespace(litellm_config=mock_config_table)
-    monkeypatch.setattr(ps, "prisma_client", mock_prisma)
-    app.dependency_overrides[ps.user_api_key_auth] = lambda: UserAPIKeyAuth(
-        user_id="admin", user_role=LitellmUserRoles.PROXY_ADMIN
-    )
-    try:
-        client = TestClient(app)
-        resp = client.get("/config/list", params={"config_type": "general_settings"})
-        assert resp.status_code == 200, resp.text
-        fields = {item["field_name"]: item for item in resp.json()}
-        assert "skip_user_budget_on_team_key" in fields
-        assert fields["skip_user_budget_on_team_key"]["field_type"] == "Boolean"
-    finally:
-        app.dependency_overrides.clear()
-
-
 def test_get_config_list_includes_budget_exceeded_throttle_percentage(monkeypatch):
     """The throttle fraction is a litellm_settings scalar surfaced on the General
     Settings table as a Float field so it sits with the other global limits; it
diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts
index d80e6177d8d..53327a9996a 100644
--- a/ui/litellm-dashboard/src/lib/http/schema.d.ts
+++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts
@@ -22666,11 +22666,6 @@ export interface components {
              * @description When set to True, rejects requests that contain client-side 'metadata.tags' to prevent users from influencing budgets by sending different tags. Tags can only be inherited from the API key metadata.
              */
             reject_clientside_metadata_tags?: boolean | null;
-            /**
-             * Skip User Budget On Team Key
-             * @description If True, restores the legacy behavior where a user's personal max_budget is NOT enforced when their key belongs to a team; only the team (and team-member) budgets apply. Defaults to False, meaning the user's personal max_budget is always enforced regardless of whether the key belongs to a team (see GitHub issue #12905).
-             */
-            skip_user_budget_on_team_key?: boolean | null;
             /**
              * Store Model In Db
              * @description If True, models and config are stored in and loaded from the database. Default is False.
diff --git a/uv.lock b/uv.lock
index 0e5b3f217d7..089718b2a88 100644
--- a/uv.lock
+++ b/uv.lock
@@ -10,7 +10,7 @@ resolution-markers = [
 ]
 
 [options]
-exclude-newer = "2026-07-25T00:00:51.267256Z"
+exclude-newer = "2026-07-27T20:58:05.848413Z"
 exclude-newer-span = "P3D"
 
 [manifest]
@@ -3966,7 +3966,7 @@ wheels = [
 
 [[package]]
 name = "litellm"
-version = "1.94.0"
+version = "1.94.1"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },