diff --git a/vllm/entrypoints/openai/api_server.py b/vllm/entrypoints/openai/api_server.py
index 3d1d832986c1e..b891debfd2b91 100644
--- a/vllm/entrypoints/openai/api_server.py
+++ b/vllm/entrypoints/openai/api_server.py
@@ -417,7 +417,13 @@ async def unload_lora_adapter(request: UnloadLoraAdapterRequest,
 
 
 def build_app(args: Namespace) -> FastAPI:
-    app = FastAPI(lifespan=lifespan)
+    if args.disable_fastapi_docs:
+        app = FastAPI(openapi_url=None,
+                      docs_url=None,
+                      redoc_url=None,
+                      lifespan=lifespan)
+    else:
+        app = FastAPI(lifespan=lifespan)
     app.include_router(router)
     app.root_path = args.root_path
 
diff --git a/vllm/entrypoints/openai/cli_args.py b/vllm/entrypoints/openai/cli_args.py
index 7ccee0b6b55b7..bbb0823de9a51 100644
--- a/vllm/entrypoints/openai/cli_args.py
+++ b/vllm/entrypoints/openai/cli_args.py
@@ -190,6 +190,13 @@ def make_arg_parser(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
                         'ID numbers being printed in log.'
                         '\n\nDefault: Unlimited')
 
+    parser.add_argument(
+        "--disable-fastapi-docs",
+        action='store_true',
+        default=False,
+        help="Disable FastAPI's OpenAPI schema, Swagger UI, and ReDoc endpoint"
+    )
+
     return parser