scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-24 00:52:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 91

refactor(vertex_ai): simplify tiered input rate selection

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-09-23 02:52:08 +00:00
parent 6e8187bbf2
commit 9e2912672d
1 changed files with 4 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

12
litellm/llms/vertex_ai/cost_calculator.py
View file

@ -191,17 +191,13 @@ def _handle_128k_pricing(
text_tokens: Final = max(usage.prompt_tokens - cache_read_tokens - cache_creation_tokens, 0)
tier_tokens: Final = max(usage.prompt_tokens - cache_creation_tokens, 0)
completion_tokens: Final = usage.completion_tokens
base_input_rate: Final = model_info["input_cost_per_token"] or 0.0
above_tier: Final = input_cost_per_token_above_128k_tokens is not None and _is_above_128k(tokens=tier_tokens)
input_rate: Final = (
input_cost_per_token_above_128k_tokens
if input_cost_per_token_above_128k_tokens is not None and _is_above_128k(tokens=tier_tokens)
else (model_info["input_cost_per_token"] or 0.0)
)
input_rate: Final = input_cost_per_token_above_128k_tokens if above_tier else base_input_rate
cache_read_rate: Final = model_info.get("cache_read_input_token_cost") or input_rate
cache_creation_rate: Final = model_info.get("cache_creation_input_token_cost") or (
model_info["input_cost_per_token"] or 0.0
)
cache_creation_rate: Final = model_info.get("cache_creation_input_token_cost") or base_input_rate
prompt_cost = (
text_tokens * input_rate + cache_read_tokens * cache_read_rate + cache_creation_tokens * cache_creation_rate