scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-15 23:31:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 165

fix: Fix cost calculation for responses

Browse source 
Signed-off-by: Adam Tao <tcx4c70@gmail.com>
This commit is contained in:
Adam Tao 2025-09-18 18:28:13 +08:00
parent bfaab8ad7e
commit f11083e992
1 changed files with 9 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
litellm/responses/utils.py
View file

@ -23,7 +23,7 @@ from litellm.types.llms.openai import (
ResponseText,
)
from litellm.types.responses.main import DecodedResponseId
from litellm.types.utils import SpecialEnums, Usage
from litellm.types.utils import PromptTokensDetails, SpecialEnums, Usage
class ResponsesAPIRequestUtils:
@ -375,8 +375,15 @@ class ResponseAPILoggingUtils:
)
prompt_tokens: int = response_api_usage.input_tokens or 0
completion_tokens: int = response_api_usage.output_tokens or 0
prompt_tokens_details: Optional[PromptTokensDetails] = None
if response_api_usage.input_tokens_details:
prompt_tokens_details = PromptTokensDetails(
cached_tokens=response_api_usage.input_tokens_details.cached_tokens,
audio_tokens=response_api_usage.input_tokens_details.audio_tokens,
)
return Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
)
prompt_tokens_details=prompt_tokens_details,
)