scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-04 02:31:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70

fix(vertex_ai): delegate web search cost to shared Gemini calculator

Browse source 
The vertex_ai cost calculator hardcoded $0.035 and charged for every
call with a PromptTokensDetailsWrapper (not just web search calls).

Delegate to the shared Gemini calculator which reads pricing and
billing unit from model_info, fixing both issues for vertex_ai models.
This commit is contained in:
Chesars 2026-03-22 18:39:12 -03:00
parent b6079018cd
commit 996d27b156
1 changed files with 10 additions and 27 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
litellm/llms/vertex_ai/gemini/cost_calculator.py
View file

@ -1,7 +1,8 @@
"""
Cost calculator for Vertex AI Gemini.
Used because there are differences in how Google AI Studio and Vertex AI Gemini handle web search requests.
Delegates to the shared Gemini cost calculator which reads pricing and
billing unit from model_info.
"""
from typing import TYPE_CHECKING
@ -14,32 +15,14 @@ def cost_per_web_search_request(usage: "Usage", model_info: "ModelInfo") -> floa
"""
Calculate the cost of a web search request for Vertex AI Gemini.
Vertex AI charges $35/1000 prompts, independent of the number of web search requests.
Billing differs by ``web_search_billing_unit`` in ``model_info``:
- ``"per_query"``: charged per individual search query (Gemini 3.x).
- ``"per_prompt"`` (default): charged per grounded prompt (Gemini 2.x).
For a single call, this is $35e-3 USD.
Args:
usage: The usage object for the web search request.
model_info: The model info for the web search request.
Returns:
The cost of the web search request.
Delegates to the shared Gemini cost calculator.
"""
from litellm.types.utils import PromptTokensDetailsWrapper
from litellm.llms.gemini.cost_calculator import (
cost_per_web_search_request as _gemini_cost,
)
# check if usage object has web search requests
cost_per_llm_call_with_web_search = 35e-3
makes_web_search_request = False
if (
usage is not None
and usage.prompt_tokens_details is not None
and isinstance(usage.prompt_tokens_details, PromptTokensDetailsWrapper)
):
makes_web_search_request = True
# Calculate total cost
if makes_web_search_request:
return cost_per_llm_call_with_web_search
else:
return 0.0
return _gemini_cost(usage=usage, model_info=model_info)