fix(cost-tracking): bill web searches reported only in server_side_tool_usage_details

litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py

@@ -2,6 +2,7 @@
 Helper utilities for tracking the cost of built-in tools.
 """
 
+from collections.abc import Mapping
 from typing import Any, Final, Literal
 
 import litellm
@@ -23,6 +24,14 @@ from litellm.types.utils import (
 )
 
 
+def _usage_reports_server_side_web_search_calls(usage: Usage) -> bool:
+    details: Final = getattr(usage, "server_side_tool_usage_details", None)
+    if not isinstance(details, Mapping):
+        return False
+    calls: Final = details.get("web_search_calls")
+    return isinstance(calls, int) and calls > 0
+
+
 class StandardBuiltInToolCostTracking:
     """
     Helper class for tracking the cost of built-in tools
@@ -351,6 +360,10 @@ class StandardBuiltInToolCostTracking:
                 # and _handle_web_search_cost() is never called.
                 if hasattr(usage, "server_tool_use") and _get_web_search_requests(usage.server_tool_use) is not None:
                     return True
+                # xAI reports usage.server_side_tool_usage_details.web_search_calls; a searched
+                # answer with no url_citation annotations has no other chat-path signal
+                if _usage_reports_server_side_web_search_calls(usage):
+                    return True
             return False
         elif isinstance(response_object, ResponsesAPIResponse):
             # response api explicitly includes web_search_call in the output
@@ -370,6 +383,8 @@ class StandardBuiltInToolCostTracking:
                 )
             ):
                 return True
+            if _usage_reports_server_side_web_search_calls(usage):
+                return True
 
         return False
 

tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py

@@ -632,3 +632,38 @@ def test_response_includes_output_type_reads_dict_output_items():
     assert not StandardBuiltInToolCostTracking.response_includes_output_type(
         response_object=response, output_type="file_search_call"
     )
+
+
+def test_web_search_gate_reads_server_side_tool_usage_details_without_citations():
+    """
+    Regression: xAI chat responses bridged from the Responses API only carry
+    usage.server_side_tool_usage_details; a searched answer with no url_citation
+    annotations must still be billed for its web search calls.
+    """
+    from litellm.llms.xai.cost_calculator import _DEFAULT_WEB_SEARCH_COST_PER_CALL
+    from litellm.types.utils import Usage
+
+    usage = Usage(
+        prompt_tokens=10,
+        completion_tokens=20,
+        total_tokens=30,
+        server_side_tool_usage_details={"web_search_calls": 3},
+    )
+    response = ModelResponse(model="xai/grok-4.5")
+
+    assert StandardBuiltInToolCostTracking.response_object_includes_web_search_call(
+        response_object=response, usage=usage
+    )
+    assert not StandardBuiltInToolCostTracking.response_object_includes_web_search_call(
+        response_object=response,
+        usage=Usage(prompt_tokens=10, completion_tokens=20, total_tokens=30),
+    )
+
+    cost = StandardBuiltInToolCostTracking.get_cost_for_built_in_tools(
+        model="xai/grok-4.5",
+        response_object=response,
+        usage=usage,
+        custom_llm_provider="xai",
+        standard_built_in_tools_params=None,
+    )
+    assert cost == 3 * _DEFAULT_WEB_SEARCH_COST_PER_CALL