diff --git a/litellm/llms/openai_like/chat/transformation.py b/litellm/llms/openai_like/chat/transformation.py
index 030710c8b2d..0ca1602ecef 100644
--- a/litellm/llms/openai_like/chat/transformation.py
+++ b/litellm/llms/openai_like/chat/transformation.py
@@ -168,3 +168,11 @@ class OpenAILikeChatConfig(OpenAIGPTConfig):
             mapped_params.pop("max_completion_tokens", None)
 
         return mapped_params
+
+
+class CustomOpenAIChatConfig(OpenAILikeChatConfig):
+    def get_models(self, api_key: str | None = None, api_base: str | None = None) -> list[str]:
+        if api_base is None:
+            raise ValueError("api_base must be set to discover models for the custom_openai provider")
+        models = super().get_models(api_key=api_key or "", api_base=api_base)
+        return [f"custom_openai/{model}" for model in models]
diff --git a/litellm/utils.py b/litellm/utils.py
index d0e11bc9551..b37d9779c10 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -8770,6 +8770,16 @@ class ProviderConfigManager:
             return litellm.InceptionTextCompletionConfig()
         return litellm.OpenAITextCompletionConfig()
 
+    @staticmethod
+    def _openai_family_model_info(provider: LlmProviders) -> BaseLLMModelInfo:
+        if provider == LlmProviders.CUSTOM_OPENAI:
+            from litellm.llms.openai_like.chat.transformation import (
+                CustomOpenAIChatConfig,
+            )
+
+            return CustomOpenAIChatConfig()
+        return litellm.OpenAIGPTConfig()
+
     @staticmethod
     def get_provider_model_info(
         model: str | None,
@@ -8777,8 +8787,8 @@ class ProviderConfigManager:
     ) -> BaseLLMModelInfo | None:
         if LlmProviders.FIREWORKS_AI == provider:
             return litellm.FireworksAIConfig()
-        elif LlmProviders.OPENAI == provider:
-            return litellm.OpenAIGPTConfig()
+        elif provider in (LlmProviders.OPENAI, LlmProviders.CUSTOM_OPENAI):
+            return ProviderConfigManager._openai_family_model_info(provider)
         elif LlmProviders.GEMINI == provider:
             return litellm.GeminiModelInfo()
         elif LlmProviders.VERTEX_AI == provider:
diff --git a/tests/litellm_utils_tests/test_utils.py b/tests/litellm_utils_tests/test_utils.py
index 0ccfae55290..8692ec7edd1 100644
--- a/tests/litellm_utils_tests/test_utils.py
+++ b/tests/litellm_utils_tests/test_utils.py
@@ -1638,6 +1638,7 @@ def test_get_valid_models_openai_proxy(monkeypatch):
         assert "litellm_proxy/gpt-5.5" in valid_models
 
 
+
 def test_get_valid_models_fireworks_ai(monkeypatch):
     from litellm.utils import get_valid_models
     import litellm
diff --git a/tests/test_litellm/llms/openai_like/chat/test_openai_like_chat_transformation.py b/tests/test_litellm/llms/openai_like/chat/test_openai_like_chat_transformation.py
index 88382b80d16..e7c71ec91be 100644
--- a/tests/test_litellm/llms/openai_like/chat/test_openai_like_chat_transformation.py
+++ b/tests/test_litellm/llms/openai_like/chat/test_openai_like_chat_transformation.py
@@ -1,5 +1,14 @@
+from unittest.mock import MagicMock, patch
+
+import litellm
 import pytest
-from litellm.llms.openai_like.chat.transformation import OpenAILikeChatConfig
+from litellm.llms.openai_like.chat.transformation import (
+    CustomOpenAIChatConfig,
+    OpenAILikeChatConfig,
+)
+from litellm.llms.openai.chat.gpt_transformation import OpenAIGPTConfig
+from litellm.types.utils import LlmProviders
+from litellm.utils import ProviderConfigManager, get_valid_models
 
 
 def test_sanitize_usage_obj_handles_null_tokens():
@@ -47,3 +56,68 @@ def test_sanitize_usage_obj_valid_usage():
 
     # Assert
     assert sanitized_json == original_json  # The object should be unchanged
+
+
+def test_get_valid_models_custom_openai():
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.json.return_value = {
+        "object": "list",
+        "data": [
+            {
+                "id": "my-custom-model",
+                "object": "model",
+                "created": 1686935002,
+                "owned_by": "organization-owner",
+            },
+        ],
+    }
+
+    with patch.object(litellm.module_level_client, "get", return_value=mock_response) as mock_get:
+        valid_models = get_valid_models(
+            check_provider_endpoint=True,
+            custom_llm_provider="custom_openai",
+            api_key="sk-1234",
+            api_base="https://my-openai-compatible-endpoint/v1",
+        )
+
+    assert valid_models == ["custom_openai/my-custom-model"]
+    mock_get.assert_called_once_with(
+        url="https://my-openai-compatible-endpoint/v1/models",
+        headers={"Authorization": "Bearer sk-1234"},
+    )
+
+
+def test_custom_openai_get_models_requires_api_base():
+    with pytest.raises(
+        ValueError,
+        match="api_base must be set to discover models for the custom_openai provider",
+    ):
+        CustomOpenAIChatConfig().get_models(api_base=None)
+
+
+def test_custom_openai_get_models_does_not_use_openai_api_key(monkeypatch):
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.json.return_value = {"data": [{"id": "my-custom-model"}]}
+    monkeypatch.setenv("OPENAI_API_KEY", "unrelated-openai-api-key")
+
+    with patch.object(litellm.module_level_client, "get", return_value=mock_response) as mock_get:
+        models = CustomOpenAIChatConfig().get_models(
+            api_base="https://my-openai-compatible-endpoint/v1"
+        )
+
+    assert models == ["custom_openai/my-custom-model"]
+    mock_get.assert_called_once_with(
+        url="https://my-openai-compatible-endpoint/v1/models",
+        headers={"Authorization": "Bearer "},
+    )
+
+
+def test_openai_model_info_uses_openai_config():
+    config = ProviderConfigManager.get_provider_model_info(
+        model=None,
+        provider=LlmProviders.OPENAI,
+    )
+
+    assert type(config) is OpenAIGPTConfig