diff --git a/litellm/proxy/auth/model_checks.py b/litellm/proxy/auth/model_checks.py
index 71ae1348f3..32f209a763 100644
--- a/litellm/proxy/auth/model_checks.py
+++ b/litellm/proxy/auth/model_checks.py
@@ -223,12 +223,14 @@ def get_known_models_from_wildcard(
     except ValueError:  # safely fail
         return []
 
-    if litellm_params is None:  # need litellm params to extract litellm model name
-        return []
-
-    try:
-        provider = litellm_params.model.split("/", 1)[0]
-    except ValueError:
+    # Use provider from litellm_params when available, otherwise from wildcard prefix
+    # (e.g., "openai" from "openai/*" - needed for BYOK where wildcard isn't in router)
+    if litellm_params is not None:
+        try:
+            provider = litellm_params.model.split("/", 1)[0]
+        except ValueError:
+            provider = wildcard_provider_prefix
+    else:
         provider = wildcard_provider_prefix
 
     # get all known provider models
@@ -282,7 +284,7 @@ def _get_wildcard_models(
             ## get litellm params from model
             if llm_router is not None:
                 model_list = llm_router.get_model_list(model_name=model)
-                if model_list is not None:
+                if model_list:
                     for router_model in model_list:
                         wildcard_models = get_known_models_from_wildcard(
                             wildcard_model=model,
@@ -291,11 +293,22 @@ def _get_wildcard_models(
                             ),
                         )
                         all_wildcard_models.extend(wildcard_models)
+                else:
+                    # Router has no deployment for this wildcard (e.g., BYOK team models)
+                    # Fall back to expanding from known provider models
+                    wildcard_models = get_known_models_from_wildcard(
+                        wildcard_model=model, litellm_params=None
+                    )
+                    if wildcard_models:
+                        models_to_remove.add(model)
+                        all_wildcard_models.extend(wildcard_models)
             else:
                 # get all known provider models
-                wildcard_models = get_known_models_from_wildcard(wildcard_model=model)
+                wildcard_models = get_known_models_from_wildcard(
+                    wildcard_model=model, litellm_params=None
+                )
 
-                if wildcard_models is not None:
+                if wildcard_models:
                     models_to_remove.add(model)
                     all_wildcard_models.extend(wildcard_models)
 
diff --git a/tests/proxy_unit_tests/test_proxy_utils.py b/tests/proxy_unit_tests/test_proxy_utils.py
index e34cad66ba..1d9bb15b21 100644
--- a/tests/proxy_unit_tests/test_proxy_utils.py
+++ b/tests/proxy_unit_tests/test_proxy_utils.py
@@ -1928,6 +1928,24 @@ def test_get_known_models_from_wildcard(
     assert all(model in wildcard_models for model in expected_models)
 
 
+def test_get_known_models_from_wildcard_without_litellm_params():
+    """
+    Test wildcard expansion without litellm_params (BYOK case - team has openai/*
+    but no deployment in router config).
+    """
+    from litellm.proxy.auth.model_checks import get_known_models_from_wildcard
+
+    wildcard_models = get_known_models_from_wildcard(
+        wildcard_model="openai/*", litellm_params=None
+    )
+    # Should return expanded OpenAI models (gpt-4o, gpt-4o-mini, etc.)
+    assert len(wildcard_models) > 0
+    assert all(m.startswith("openai/") for m in wildcard_models)
+    # Check for common OpenAI models
+    model_ids = [m.split("/", 1)[1] for m in wildcard_models]
+    assert "gpt-4o" in model_ids or "gpt-3.5-turbo" in model_ids
+
+
 @pytest.mark.parametrize(
     "data, user_api_key_dict, expected_model",
     [
diff --git a/tests/test_litellm/proxy/auth/test_model_checks.py b/tests/test_litellm/proxy/auth/test_model_checks.py
index 789af480e7..193b014f03 100644
--- a/tests/test_litellm/proxy/auth/test_model_checks.py
+++ b/tests/test_litellm/proxy/auth/test_model_checks.py
@@ -62,3 +62,27 @@ def test_get_complete_model_list_order(key_models, team_models, proxy_model_list
         infer_model_from_keys=False,
         llm_router=Router(model_list=model_list),
     ) == expected
+
+
+def test_get_complete_model_list_byok_wildcard_expansion():
+    """
+    Test that wildcard models (e.g., openai/*) are expanded when the router has
+    no deployment for them - BYOK case where team has openai/* but proxy has
+    no openai config.
+    """
+    from litellm.proxy.auth.model_checks import get_complete_model_list
+    from litellm import Router
+
+    # Router with empty model_list - no openai/* deployment (BYOK scenario)
+    result = get_complete_model_list(
+        key_models=[],
+        team_models=["openai/*"],
+        proxy_model_list=[],
+        user_model=None,
+        infer_model_from_keys=False,
+        llm_router=Router(model_list=[]),
+    )
+    # Should expand openai/* to actual OpenAI models
+    assert len(result) > 0
+    assert all(m.startswith("openai/") for m in result)
+    assert "openai/*" not in result