phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-24 10:14:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge 24101fc7af into b82af5b826

Browse source
This commit is contained in:
yeahyung 2025-04-24 00:59:03 -07:00 • committed by GitHub
commit 7320f38f61
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

6
litellm/cost_calculator.py
View file

@ -319,7 +319,7 @@ def cost_per_token( # noqa: PLR0915
if model_info["input_cost_per_token"] > 0:
## COST PER TOKEN ##
prompt_tokens_cost_usd_dollar = (
model_info["input_cost_per_token"] * prompt_tokens
model_info["input_cost_per_token"] * (prompt_tokens - cache_read_input_tokens)
)
elif (
model_info.get("input_cost_per_second", None) is not None
@ -335,6 +335,10 @@ def cost_per_token( # noqa: PLR0915
prompt_tokens_cost_usd_dollar = (
model_info["input_cost_per_second"] * response_time_ms / 1000 # type: ignore
)
## Prompt Caching cost calculation
if model_info["cache_read_input_token_cost"] is not None and model_info["cache_read_input_token_cost"] > 0:
## COST PER TOKEN ##
prompt_tokens_cost_usd_dollar += model_info["cache_read_input_token_cost"] * cache_read_input_tokens
if model_info["output_cost_per_token"] > 0:
completion_tokens_cost_usd_dollar = (