Merge pull request #35140 from BerriAI/litellm_fix_file_content_placeholder_cost

fix(cost): stop token-pricing the placeholder input on file content calls

litellm/litellm_core_utils/litellm_logging.py

@@ -1399,10 +1399,7 @@ class Logging(LiteLLMLoggingBaseClass):
             litellm_params=(self.litellm_params if hasattr(self, "litellm_params") else None)
         )
 
-        prompt = ""  # use for tts cost calc
-        _input: Final = self.model_call_details.get("input", None)
-        if _input is not None and isinstance(_input, str):
-            prompt = _input
+        prompt = self._prompt_for_cost_calculation()
 
         if cache_hit is None:
             cache_hit = self.model_call_details.get("cache_hit", False)
@@ -1461,6 +1458,19 @@ class Logging(LiteLLMLoggingBaseClass):
 
         return None
 
+    def _prompt_for_cost_calculation(self) -> str:
+        """
+        The raw input string is only priced directly for text-to-speech, which bills per character.
+        Every other call type gets its billable units from the response usage object, and call types
+        that carry no usage at all (file content retrieval, and anything else `function_setup` cannot
+        build messages for) only have the ``"default-message-value"`` placeholder here, so passing the
+        input along would token-price that placeholder.
+        """
+        if self.call_type not in (CallTypes.speech.value, CallTypes.aspeech.value):
+            return ""
+        _input = self.model_call_details.get("input", None)
+        return _input if isinstance(_input, str) else ""
+
     def _generate_content_result_as_model_response(self, result: object) -> ModelResponse | None:
         """
         Native Google :generateContent bodies report token usage under

tests/test_litellm/litellm_core_utils/test_litellm_logging.py

@@ -11,6 +11,9 @@ sys.path.insert(
 
 import time
 
+import httpx
+from openai._legacy_response import HttpxBinaryResponseContent
+
 import litellm
 from litellm.constants import SENTRY_DENYLIST, SENTRY_PII_DENYLIST
 from litellm.integrations.custom_logger import CustomLogger
@@ -1771,6 +1774,60 @@ def test_response_cost_calculator_does_not_transform_non_generate_content_dict()
     assert not cost
 
 
+def _file_content_logging_obj(call_type: str) -> LitellmLogging:
+    logging_obj = LitellmLogging(
+        model="gemini-3-flash-preview",
+        messages="default-message-value",
+        stream=False,
+        call_type=call_type,
+        start_time=time.time(),
+        litellm_call_id=f"file-content-{call_type}",
+        function_id=f"file-content-{call_type}",
+    )
+    logging_obj.model_call_details["custom_llm_provider"] = "vertex_ai"
+    logging_obj.model_call_details["input"] = "default-message-value"
+    logging_obj.optional_params = {}
+    return logging_obj
+
+
+@pytest.mark.parametrize("call_type", ["afile_content", "file_content"])
+def test_file_content_call_is_not_billed(call_type):
+    """
+    Regression for #35130: file content retrieval has no token usage, but ``function_setup``
+    stores the ``"default-message-value"`` placeholder as the logged input, which the cost
+    calculator then token-priced, billing every call at exactly 3 * input_cost_per_token.
+    """
+    result = HttpxBinaryResponseContent(httpx.Response(status_code=200, content=b"file contents"))
+
+    cost = _file_content_logging_obj(call_type)._response_cost_calculator(result=result)
+
+    assert cost == 0.0
+
+
+@pytest.mark.parametrize("call_type", ["aspeech", "speech"])
+def test_speech_call_is_still_priced_from_input_characters(call_type):
+    """tts bills per input character, so speech call types must keep passing the input along."""
+    logging_obj = LitellmLogging(
+        model="tts-1",
+        messages="the quick brown fox jumped over the lazy dogs",
+        stream=False,
+        call_type=call_type,
+        start_time=time.time(),
+        litellm_call_id=f"speech-{call_type}",
+        function_id=f"speech-{call_type}",
+    )
+    logging_obj.model_call_details["custom_llm_provider"] = "openai"
+    logging_obj.model_call_details["input"] = "the quick brown fox jumped over the lazy dogs"
+    logging_obj.optional_params = {}
+
+    result = HttpxBinaryResponseContent(httpx.Response(status_code=200, content=b"audio bytes"))
+
+    cost = logging_obj._response_cost_calculator(result=result)
+
+    assert cost is not None
+    assert cost > 0
+
+
 def test_sentry_event_scrubber_initialization(monkeypatch):
     # Step 1: Create a fake sentry_sdk.scrubber module
     mock_event_scrubber_instance = MagicMock()