diff --git a/litellm/llms/fireworks_ai/chat/transformation.py b/litellm/llms/fireworks_ai/chat/transformation.py
index 4740e84d513..a05b160413e 100644
--- a/litellm/llms/fireworks_ai/chat/transformation.py
+++ b/litellm/llms/fireworks_ai/chat/transformation.py
@@ -295,7 +295,7 @@ class FireworksAIConfig(FireworksAIMixin, OpenAIGPTConfig):
                     optional_params["reasoning_effort"] = "medium"
                 elif value is False:
                     optional_params["reasoning_effort"] = "none"
-                else:
+                elif value != "auto":
                     optional_params["reasoning_effort"] = value
             elif param in supported_openai_params:
                 if value is not None:
@@ -303,7 +303,9 @@ class FireworksAIConfig(FireworksAIMixin, OpenAIGPTConfig):
 
         return optional_params
 
-    def map_extra_body_params(self, optional_params: Mapping[str, object], model: str) -> dict:  # noqa: LIT001  # http handler pops extra_body off the returned dict
+    def map_extra_body_params(
+        self, optional_params: Mapping[str, object], model: str
+    ) -> dict:  # mutable-ok: http handler pops extra_body off the returned dict
         extra_body: Final = optional_params.get("extra_body")
         if not isinstance(extra_body, dict):
             return dict(optional_params)  # mutable-ok: JSON request body
diff --git a/tests/test_litellm/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py b/tests/test_litellm/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py
index 3fbbc70916a..bbb7fb197d0 100644
--- a/tests/test_litellm/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py
+++ b/tests/test_litellm/llms/fireworks_ai/chat/test_fireworks_ai_chat_transformation.py
@@ -1153,6 +1153,22 @@ def test_reasoning_effort_integer_passthrough():
     assert isinstance(result["reasoning_effort"], int)
 
 
+def test_reasoning_effort_auto_dropped_to_model_default():
+    """
+    Fireworks rejects reasoning_effort="auto" (accepted set: low/medium/high/
+    xhigh/max/none/adaptive). Omitting the param is the model default, which is
+    exactly what "auto" means on OpenAI's side, so it must not reach the request.
+    """
+    config = FireworksAIConfig()
+    result = config.map_openai_params(
+        {"reasoning_effort": "auto"},
+        {},
+        _REASONING_MODEL,
+        drop_params=False,
+    )
+    assert "reasoning_effort" not in result
+
+
 def test_transform_response_captures_perf_metrics():
     body = {
         **_BASE_CHAT_COMPLETION_RESPONSE,