scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-06 02:48:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

feat(cost-calculator): compute and store per-type cache costs in CostBreakdown (cache_read_cost, cache_creation_cost)

Browse source
This commit is contained in:
Ishaan Jaffer 2026-04-14 18:20:40 -07:00
parent b5a4c26248
commit 781fc6311b
No known key found for this signature in database
1 changed files with 20 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

20
litellm/cost_calculator.py
View file

@ -966,6 +966,8 @@ def _store_cost_breakdown_in_logging_obj(
margin_percent: Optional[float] = None,
margin_fixed_amount: Optional[float] = None,
margin_total_amount: Optional[float] = None,
cache_read_cost: Optional[float] = None,
cache_creation_cost: Optional[float] = None,
) -> None:
"""
Helper function to store cost breakdown in the logging object.
@ -1001,6 +1003,8 @@ def _store_cost_breakdown_in_logging_obj(
margin_percent=margin_percent,
margin_fixed_amount=margin_fixed_amount,
margin_total_amount=margin_total_amount,
cache_read_cost=cache_read_cost,
cache_creation_cost=cache_creation_cost,
)
except Exception as breakdown_error:
@ -1599,6 +1603,20 @@ def completion_cost( # noqa: PLR0915
# Store cost breakdown in logging object if available
if litellm_logging_obj is not None:
_cache_read_cost: Optional[float] = None
_cache_creation_cost: Optional[float] = None
if cost_per_token_usage_object is not None:
_cr = getattr(cost_per_token_usage_object, "cache_read_input_tokens", None) or (cost_per_token_usage_object.model_extra or {}).get("cache_read_input_tokens")
_cc = getattr(cost_per_token_usage_object, "cache_creation_input_tokens", None) or (cost_per_token_usage_object.model_extra or {}).get("cache_creation_input_tokens")
if (_cr or _cc) and model:
try:
_mi = litellm.get_model_info(model=model, custom_llm_provider=custom_llm_provider)
if _cr and _mi.get("cache_read_input_token_cost"):
_cache_read_cost = float(_cr) * float(_mi["cache_read_input_token_cost"])
if _cc and _mi.get("cache_creation_input_token_cost"):
_cache_creation_cost = float(_cc) * float(_mi["cache_creation_input_token_cost"])
except Exception:
pass
_store_cost_breakdown_in_logging_obj(
litellm_logging_obj=litellm_logging_obj,
prompt_tokens_cost_usd_dollar=prompt_tokens_cost_usd_dollar,
@ -1612,6 +1630,8 @@ def completion_cost( # noqa: PLR0915
margin_percent=margin_percent,
margin_fixed_amount=margin_fixed_amount,
margin_total_amount=margin_total_amount,
cache_read_cost=_cache_read_cost,
cache_creation_cost=_cache_creation_cost,
)
return _final_cost