scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49

fix(vertex_ai): preserve tiered rate type narrowing

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 02:58:55 +00:00
parent 9e2912672d
commit 1248c93567
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/llms/vertex_ai/cost_calculator.py
View file

@ -194,7 +194,7 @@ def _handle_128k_pricing(
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 above_tier else base_input_rate
input_rate: Final = (input_cost_per_token_above_128k_tokens or base_input_rate) 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 base_input_rate