diff --git a/litellm/proxy/_types.py b/litellm/proxy/_types.py
index 23fe7af9994..f0cefb2d55b 100644
--- a/litellm/proxy/_types.py
+++ b/litellm/proxy/_types.py
@@ -287,6 +287,8 @@ class LiteLLMRoutes(enum.Enum):
         "/chat/completions",
         "/v1/chat/completions",
         "/cursor/chat/completions",
+        "/cursor/models",
+        "/cursor/v1/models",
         # completions
         "/engines/{model}/completions",
         "/openai/deployments/{model}/completions",
diff --git a/litellm/proxy/response_api_endpoints/endpoints.py b/litellm/proxy/response_api_endpoints/endpoints.py
index 9601e2d4fde..80abdab8583 100644
--- a/litellm/proxy/response_api_endpoints/endpoints.py
+++ b/litellm/proxy/response_api_endpoints/endpoints.py
@@ -22,6 +22,8 @@ from litellm.types.responses.main import DeleteResponseResult
 
 router = APIRouter()
 
+_user_api_key_auth_dep = Depends(user_api_key_auth)
+
 
 @router.post(
     "/v1/responses",
@@ -283,6 +285,33 @@ async def responses_api(
         )
 
 
+@router.get(
+    "/cursor/models",
+    dependencies=[Depends(user_api_key_auth)],
+    tags=["responses"],
+)
+@router.get(
+    "/cursor/v1/models",
+    dependencies=[Depends(user_api_key_auth)],
+    tags=["responses"],
+)
+async def cursor_model_list(
+    user_api_key_dict: UserAPIKeyAuth = _user_api_key_auth_dep,
+):
+    """
+    OpenAI-compatible model listing for the Cursor BYOK base URL.
+
+    Clients pointed at `<proxy>/cursor` as an OpenAI-compatible base URL resolve and
+    verify models via `GET {base}/models` (the OpenAI SDK contract). Without this
+    route those requests fall through to the Cursor Cloud Agents passthrough, which
+    demands a Cursor API key and 401s, so key verification silently fails before any
+    chat request is ever sent. Delegates to the standard `/v1/models` handler.
+    """
+    from litellm.proxy.proxy_server import model_list
+
+    return await model_list(user_api_key_dict=user_api_key_dict)
+
+
 @router.post(
     "/cursor/chat/completions",
     dependencies=[Depends(user_api_key_auth)],
diff --git a/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py b/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py
index 0cc79658b6a..c41de4a8e40 100644
--- a/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py
+++ b/tests/test_litellm/proxy/response_api_endpoints/test_endpoints.py
@@ -881,3 +881,29 @@ def test_cursor_chat_completions_input_body_uses_responses_pipeline_and_strips_s
     followup_body = asyncio.run(real_read_request_body(request=captured_requests[0]))
     assert followup_body.get("stream_options") == {"include_usage": True}
     assert followup_body.get("input") == [{"role": "user", "content": "hello"}]
+
+
+def test_cursor_models_route_delegates_to_model_list():
+    """Clients pointed at <proxy>/cursor as an OpenAI-compatible base URL resolve and
+    verify keys via GET {base}/models (the OpenAI SDK contract). Without a dedicated
+    route those requests fall through to the Cursor Cloud Agents passthrough and 401
+    for lack of a Cursor API key, so BYOK verification fails before any chat request
+    is sent. Both /cursor/models and /cursor/v1/models must serve the standard model
+    list instead."""
+    from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
+
+    import litellm.proxy.proxy_server as ps
+
+    model_payload = {"data": [{"id": "gpt-5.6", "object": "model"}], "object": "list"}
+
+    app.dependency_overrides[user_api_key_auth] = _auth_override
+    try:
+        with patch.object(ps, "model_list", AsyncMock(return_value=model_payload)) as mock_model_list:
+            client = TestClient(app)
+            for path in ("/cursor/models", "/cursor/v1/models"):
+                response = client.get(path, headers={"Authorization": "Bearer sk-test-cursor"})
+                assert response.status_code == 200, f"{path}: {response.text}"
+                assert response.json() == model_payload
+            assert mock_model_list.call_count == 2
+    finally:
+        app.dependency_overrides.pop(user_api_key_auth, None)
diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts
index 4e0b9b88995..1bc8839976d 100644
--- a/ui/litellm-dashboard/src/lib/http/schema.d.ts
+++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts
@@ -2645,6 +2645,58 @@ export interface paths {
         patch?: never;
         trace?: never;
     };
+    "/cursor/models": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /**
+         * Cursor Model List
+         * @description OpenAI-compatible model listing for the Cursor BYOK base URL.
+         *
+         *     Clients pointed at `<proxy>/cursor` as an OpenAI-compatible base URL resolve and
+         *     verify models via `GET {base}/models` (the OpenAI SDK contract). Without this
+         *     route those requests fall through to the Cursor Cloud Agents passthrough, which
+         *     demands a Cursor API key and 401s, so key verification silently fails before any
+         *     chat request is ever sent. Delegates to the standard `/v1/models` handler.
+         */
+        get: operations["cursor_model_list_cursor_models_get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
+    "/cursor/v1/models": {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        /**
+         * Cursor Model List
+         * @description OpenAI-compatible model listing for the Cursor BYOK base URL.
+         *
+         *     Clients pointed at `<proxy>/cursor` as an OpenAI-compatible base URL resolve and
+         *     verify models via `GET {base}/models` (the OpenAI SDK contract). Without this
+         *     route those requests fall through to the Cursor Cloud Agents passthrough, which
+         *     demands a Cursor API key and 401s, so key verification silently fails before any
+         *     chat request is ever sent. Delegates to the standard `/v1/models` handler.
+         */
+        get: operations["cursor_model_list_cursor_v1_models_get"];
+        put?: never;
+        post?: never;
+        delete?: never;
+        options?: never;
+        head?: never;
+        patch?: never;
+        trace?: never;
+    };
     "/cursor/{endpoint}": {
         parameters: {
             query?: never;
@@ -38506,6 +38558,46 @@ export interface operations {
             };
         };
     };
+    cursor_model_list_cursor_models_get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": unknown;
+                };
+            };
+        };
+    };
+    cursor_model_list_cursor_v1_models_get: {
+        parameters: {
+            query?: never;
+            header?: never;
+            path?: never;
+            cookie?: never;
+        };
+        requestBody?: never;
+        responses: {
+            /** @description Successful Response */
+            200: {
+                headers: {
+                    [name: string]: unknown;
+                };
+                content: {
+                    "application/json": unknown;
+                };
+            };
+        };
+    };
     cursor_proxy_route_cursor__endpoint__get: {
         parameters: {
             query?: never;