phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

test(utils.py): handle scenario where text tokens + reasoning tokens … (#10165)

Browse source 
* test(utils.py): handle scenario where text tokens + reasoning tokens set, but reasoning tokens not charged separately

Addresses https://github.com/BerriAI/litellm/pull/10141#discussion_r2051555332

* fix(vertex_and_google_ai_studio.py): only set content if non-empty str
This commit is contained in:
Krish Dholakia 2025-04-19 12:32:38 -07:00 • committed by GitHub
parent 99db1b7690
commit 03b5399f86
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 90 additions and 49 deletions
Download patch file Download diff file Expand all files Collapse all files

32
litellm/litellm_core_utils/llm_cost_calc/utils.py
View file

@ -265,9 +265,10 @@ def generic_cost_per_token(
)
## CALCULATE OUTPUT COST
text_tokens = usage.completion_tokens
text_tokens = 0
audio_tokens = 0
reasoning_tokens = 0
is_text_tokens_total = False
if usage.completion_tokens_details is not None:
audio_tokens = (
cast(
@ -281,7 +282,7 @@ def generic_cost_per_token(
Optional[int],
getattr(usage.completion_tokens_details, "text_tokens", None),
)
or usage.completion_tokens # default to completion tokens, if this field is not set
or 0 # default to completion tokens, if this field is not set
)
reasoning_tokens = (
cast(
@ -290,6 +291,11 @@ def generic_cost_per_token(
)
or 0
)
if text_tokens == 0:
text_tokens = usage.completion_tokens
if text_tokens == usage.completion_tokens:
is_text_tokens_total = True
## TEXT COST
completion_cost = float(text_tokens) * completion_base_cost
@ -302,19 +308,21 @@ def generic_cost_per_token(
)
## AUDIO COST
if (
_output_cost_per_audio_token is not None
and audio_tokens is not None
and audio_tokens > 0
):
if not is_text_tokens_total and audio_tokens is not None and audio_tokens > 0:
_output_cost_per_audio_token = (
_output_cost_per_audio_token
if _output_cost_per_audio_token is not None
else completion_base_cost
)
completion_cost += float(audio_tokens) * _output_cost_per_audio_token
## REASONING COST
if (
_output_cost_per_reasoning_token is not None
and reasoning_tokens
and reasoning_tokens > 0
):
if not is_text_tokens_total and reasoning_tokens and reasoning_tokens > 0:
_output_cost_per_reasoning_token = (
_output_cost_per_reasoning_token
if _output_cost_per_reasoning_token is not None
else completion_base_cost
)
completion_cost += float(reasoning_tokens) * _output_cost_per_reasoning_token
return prompt_cost, completion_cost