diff --git a/litellm/router.py b/litellm/router.py
index 81e49645462..6eadaaa9913 100644
--- a/litellm/router.py
+++ b/litellm/router.py
@@ -2172,9 +2172,8 @@ class Router:
                 "messages": messages,
                 "caching": self.cache_responses,
                 "client": model_client,
-                **kwargs,
+                **{k: v for k, v in kwargs.items() if k != "_target_order"},
             }
-            input_kwargs.pop("_target_order", None)
             response: Final = litellm.completion(**input_kwargs)
             verbose_router_logger.info("litellm.completion(model=%s)\x1b[32m 200 OK\x1b[0m", model_name)
 
@@ -3194,11 +3193,10 @@ class Router:
                 "messages": messages,
                 "caching": self.cache_responses,
                 "client": model_client,
-                **kwargs,
+                **{k: v for k, v in kwargs.items() if k != "_target_order"},
             }
             input_kwargs.pop("silent_model", None)
             input_kwargs.pop("include_fallback_errors", None)
-            input_kwargs.pop("_target_order", None)
 
             _response: Final = litellm.acompletion(**input_kwargs)
 
diff --git a/litellm/router_utils/fallback_event_handlers.py b/litellm/router_utils/fallback_event_handlers.py
index c37fbdc8ed7..8c33bf1481f 100644
--- a/litellm/router_utils/fallback_event_handlers.py
+++ b/litellm/router_utils/fallback_event_handlers.py
@@ -412,11 +412,10 @@ async def run_async_fallback(
             # LOGGING
             kwargs = litellm_router.log_retry(kwargs=kwargs, e=original_exception)
             verbose_router_logger.info("Falling back to model_group = %s", mask_sensitive_structure(mg))
+            kwargs = {k: v for k, v in kwargs.items() if k != "_target_order"}  # rebind-ok: next hop must not inherit the previous order target
             if isinstance(mg, str):
                 kwargs["model"] = mg
-                kwargs.pop("_target_order", None)
             elif isinstance(mg, dict):
-                kwargs.pop("_target_order", None)
                 kwargs.update(mg)
             fallback_depth = fallback_depth + 1
             _hop_metadata = dict(kwargs.get(metadata_variable_name) or {})
diff --git a/tests/test_litellm/test_router_order_fallback.py b/tests/test_litellm/test_router_order_fallback.py
index 33916444003..d74e0a6ffa4 100644
--- a/tests/test_litellm/test_router_order_fallback.py
+++ b/tests/test_litellm/test_router_order_fallback.py
@@ -14,6 +14,7 @@ import litellm
 from litellm import Router
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.router_utils.prompt_caching_cache import PromptCachingCache
+from litellm.types.router import RouterRateLimitError
 from litellm.utils import _get_deployment_order, _get_order_filtered_deployments
 
 # ---------------------------------------------------------------------------
@@ -454,13 +455,12 @@ async def test_router_order_fallback_does_not_reselect_order_1_when_order_2_is_f
     )
     litellm.callbacks.append(drop_order_2)
     try:
-        with pytest.raises(Exception) as exc_info:
+        with pytest.raises(RouterRateLimitError, match="No deployments available") as exc_info:
             await router.acompletion(
                 model="test-model",
                 messages=[{"role": "user", "content": "hi"}],
             )
         assert "success from order 2" not in str(exc_info.value)
-        assert getattr(exc_info.value, "_hidden_params", {}).get("model_id") != "1"
     finally:
         litellm.callbacks.remove(drop_order_2)