[Feat] OTEL - Log Cost Breakdown on OTEL Logger (#16334)

* add gen_ai cost metrics

* TestOpenTelemetryCostBreakdown

* fix QA check

* validate_redacted_message_span_attributes

litellm/integrations/opentelemetry.py

@@ -10,6 +10,7 @@ from litellm.litellm_core_utils.safe_json_dumps import safe_dumps
 from litellm.types.services import ServiceLoggerPayload
 from litellm.types.utils import (
     ChatCompletionMessageToolCall,
+    CostBreakdown,
     Function,
     StandardCallbackDynamicParams,
     StandardLoggingPayload,
@@ -1076,6 +1077,16 @@ class OpenTelemetry(CustomLogger):
                 self.safe_set_attribute(
                     span=span, key="hidden_params", value=safe_dumps(hidden_params)
                 )
+            # Cost breakdown tracking
+            cost_breakdown: Optional[CostBreakdown] = standard_logging_payload.get("cost_breakdown")
+            if cost_breakdown:
+                for key, value in cost_breakdown.items():
+                    if value is not None:
+                        self.safe_set_attribute(
+                            span=span,
+                            key=f"gen_ai.cost.{key}",
+                            value=value,
+                        )
             #############################################
             ########## LLM Request Attributes ###########
             #############################################

litellm/llms/xai/responses/transformation.py

@@ -85,7 +85,7 @@ class XAIResponsesAPIConfig(OpenAIResponsesAPIConfig):
                     # XAI supports code_interpreter but doesn't use the container field
                     # Keep only the type field
                     verbose_logger.debug(
-                        f"XAI: Transforming code_interpreter tool, removing container field"
+                        "XAI: Transforming code_interpreter tool, removing container field"
                     )
                     transformed_tools.append({"type": "code_interpreter"})
                 else:

litellm/model_prices_and_context_window_backup.json

@@ -3704,7 +3704,6 @@
         "output_cost_per_token": 2.75e-05,
         "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/",
         "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_web_search": true
@@ -3732,7 +3731,6 @@
         "mode": "chat",
         "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-the-grok-4-fast-models-from-xai-now-available-in-azure-ai-foundry/4456701",
         "supports_function_calling": true,
-        "supports_reasoning": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_web_search": true

tests/logging_callback_tests/test_otel_logging.py

@@ -281,11 +281,13 @@ def validate_redacted_message_span_attributes(span):
         _all_attributes
     ), f"Missing required attributes: {required_set - _all_attributes}"
 
-    # Check that any additional attributes are metadata fields (start with "metadata.")
+    # Check that any additional attributes are metadata fields (start with "metadata.") or cost fields
     non_required_attrs = _all_attributes - required_set
     for attr in non_required_attrs:
-        assert attr.startswith("metadata.") or attr.startswith(
-            "hidden_params"
+        assert (
+            attr.startswith("metadata.")
+            or attr.startswith("hidden_params")
+            or attr.startswith("gen_ai.cost.")
         ), f"Non-metadata attribute found: {attr}"
 
     pass

tests/test_litellm/integrations/test_opentelemetry.py

@@ -79,6 +79,98 @@ class TestOpenTelemetryGuardrails(unittest.TestCase):
         otel.tracer.start_span.assert_not_called()
 
 
+class TestOpenTelemetryCostBreakdown(unittest.TestCase):
+    def test_cost_breakdown_emitted_to_otel_span(self):
+        """
+        Test that cost breakdown from StandardLoggingPayload is emitted to OpenTelemetry span attributes.
+        """
+        otel = OpenTelemetry()
+        mock_span = MagicMock()
+
+        cost_breakdown = {
+            "input_cost": 0.001,
+            "output_cost": 0.002,
+            "total_cost": 0.003,
+            "tool_usage_cost": 0.0001,
+            "original_cost": 0.004,
+            "discount_percent": 0.25,
+            "discount_amount": 0.001,
+        }
+
+        kwargs = {
+            "model": "gpt-4",
+            "messages": [{"role": "user", "content": "Hello"}],
+            "optional_params": {},
+            "litellm_params": {"custom_llm_provider": "openai"},
+            "standard_logging_object": {
+                "id": "test-id",
+                "call_type": "completion",
+                "metadata": {},
+                "cost_breakdown": cost_breakdown,
+            },
+        }
+
+        response_obj = {
+            "id": "test-response-id",
+            "model": "gpt-4",
+            "choices": [],
+            "usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30},
+        }
+
+        otel.set_attributes(span=mock_span, kwargs=kwargs, response_obj=response_obj)
+
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.input_cost", 0.001)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.output_cost", 0.002)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.total_cost", 0.003)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.tool_usage_cost", 0.0001)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.original_cost", 0.004)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.discount_percent", 0.25)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.discount_amount", 0.001)
+
+    def test_cost_breakdown_with_partial_fields(self):
+        """
+        Test that cost breakdown works correctly when only some fields are present.
+        """
+        otel = OpenTelemetry()
+        mock_span = MagicMock()
+
+        cost_breakdown = {
+            "input_cost": 0.001,
+            "output_cost": 0.002,
+            "total_cost": 0.003,
+        }
+
+        kwargs = {
+            "model": "gpt-4",
+            "messages": [{"role": "user", "content": "Hello"}],
+            "optional_params": {},
+            "litellm_params": {"custom_llm_provider": "openai"},
+            "standard_logging_object": {
+                "id": "test-id",
+                "call_type": "completion",
+                "metadata": {},
+                "cost_breakdown": cost_breakdown,
+            },
+        }
+
+        response_obj = {
+            "id": "test-response-id",
+            "model": "gpt-4",
+            "choices": [],
+            "usage": {"prompt_tokens": 10, "completion_tokens": 20, "total_tokens": 30},
+        }
+
+        otel.set_attributes(span=mock_span, kwargs=kwargs, response_obj=response_obj)
+
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.input_cost", 0.001)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.output_cost", 0.002)
+        mock_span.set_attribute.assert_any_call("gen_ai.cost.total_cost", 0.003)
+
+        call_args_list = [call[0] for call in mock_span.set_attribute.call_args_list]
+        assert ("gen_ai.cost.tool_usage_cost", 0.0001) not in call_args_list
+        assert ("gen_ai.cost.original_cost", 0.004) not in call_args_list
+
+
 class TestOpenTelemetry(unittest.TestCase):
     POLL_INTERVAL = 0.05
     POLL_TIMEOUT = 2.0