[Bug]: Error creating standard logging object - ResponseAPIUsage missing total_tokens #13697
Description
What happened?
Hi there,
I see a lot of errors like this:
{"message":{"level":"ERROR","message":"Error creating standard logging object - 1 validation error for ResponseAPIUsage\ntotal_tokens\n Field required [type=missing, input_value={'input_tokens': 34797, 'output_tokens': 42}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.10/v/missing","stacktrace":"Traceback (most recent call last):\n File \"/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/litellm_logging.py\", line 4341, in get_standard_logging_object_payload\n usage = StandardLoggingPayloadSetup.get_usage_from_response_obj(\n response_obj=response_obj,\n ...<2 lines>...\n ),\n )\n File \"/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/litellm_logging.py\", line 3959, in get_usage_from_response_obj\n ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^\n usage\n ^^^^^\n )\n ^\n File \"/usr/lib/python3.13/site-packages/litellm/responses/utils.py\", line 251, in _transform_response_api_usage_to_chat_usage\n ResponseAPIUsage(**usage) if isinstance(usage, dict) else usage\n ~~~~~~~~~~~~~~~~^^^^^^^^^\n File \"/usr/lib/python3.13/site-packages/pydantic/main.py\", line 214, in __init__\n validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)\npydantic_core._pydantic_core.ValidationError: 1 validation error for ResponseAPIUsage\ntotal_tokens\n Field required [type=missing, input_value={'input_tokens': 34797, 'output_tokens': 42}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.10/v/missing","timestamp":"2025-08-18T11:09:20.739871"},"stream":"stderr"}
{"message":{"level":"ERROR","message":"Error creating standard logging object - 1 validation error for ResponseAPIUsage\ntotal_tokens\n Field required [type=missing, input_value={'input_tokens': 15290, 'output_tokens': 37}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.10/v/missing","stacktrace":"Traceback (most recent call last):\n File \"/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/litellm_logging.py\", line 4341, in get_standard_logging_object_payload\n usage = StandardLoggingPayloadSetup.get_usage_from_response_obj(\n response_obj=response_obj,\n ...<2 lines>...\n ),\n )\n File \"/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/litellm_logging.py\", line 3959, in get_usage_from_response_obj\n ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^\n usage\n ^^^^^\n )\n ^\n File \"/usr/lib/python3.13/site-packages/litellm/responses/utils.py\", line 251, in _transform_response_api_usage_to_chat_usage\n ResponseAPIUsage(**usage) if isinstance(usage, dict) else usage\n ~~~~~~~~~~~~~~~~^^^^^^^^^\n File \"/usr/lib/python3.13/site-packages/pydantic/main.py\", line 214, in __init__\n validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)\npydantic_core._pydantic_core.ValidationError: 1 validation error for ResponseAPIUsage\ntotal_tokens\n Field required [type=missing, input_value={'input_tokens': 15290, 'output_tokens': 37}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.10/v/missing","timestamp":"2025-08-18T11:08:57.878333"},"stream":"stderr"}
{"message":{"level":"ERROR","message":"Error creating standard logging object - 1 validation error for ResponseAPIUsage\ntotal_tokens\n Field required [type=missing, input_value={'input_tokens': 14414, 'output_tokens': 75}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.10/v/missing","stacktrace":"Traceback (most recent call last):\n File \"/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/litellm_logging.py\", line 4341, in get_standard_logging_object_payload\n usage = StandardLoggingPayloadSetup.get_usage_from_response_obj(\n response_obj=response_obj,\n ...<2 lines>...\n ),\n )\n File \"/usr/lib/python3.13/site-packages/litellm/litellm_core_utils/litellm_logging.py\", line 3959, in get_usage_from_response_obj\n ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(\n ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^\n usage\n ^^^^^\n )\n ^\n File \"/usr/lib/python3.13/site-packages/litellm/responses/utils.py\", line 251, in _transform_response_api_usage_to_chat_usage\n ResponseAPIUsage(**usage) if isinstance(usage, dict) else usage\n ~~~~~~~~~~~~~~~~^^^^^^^^^\n File \"/usr/lib/python3.13/site-packages/pydantic/main.py\", line 214, in __init__\n validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)\npydantic_core._pydantic_core.ValidationError: 1 validation error for ResponseAPIUsage\ntotal_tokens\n Field required [type=missing, input_value={'input_tokens': 14414, 'output_tokens': 75}, input_type=dict]\n For further information visit https://errors.pydantic.dev/2.10/v/missing","timestamp":"2025-08-18T11:08:54.802808"},"stream":"stderr"}
I'm using claude code with openai compatible models.
Relevant log output
Are you a ML Ops Team?
No
What LiteLLM version are you on ?
1.75.5-stable
Twitter / LinkedIn details
No response