scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-19 00:01:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 122

fix(cost_map): vertex gemini-3.5-flash-lite priority cache read is $0.054/M

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-09-14 22:14:56 +00:00
parent 7fd541efb9
commit 18d85c7203
3 changed files with 5 additions and 5 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
litellm/model_prices_and_context_window_backup.json
View file

@ -24134,7 +24134,7 @@
"deprecation_date": "2027-07-21",
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 1.5e-08,
"cache_read_input_token_cost_priority": 5e-08,
"cache_read_input_token_cost_priority": 5.4e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,
@ -47858,7 +47858,7 @@
"deprecation_date": "2027-07-21",
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 1.5e-08,
"cache_read_input_token_cost_priority": 5e-08,
"cache_read_input_token_cost_priority": 5.4e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,

4
model_prices_and_context_window.json
View file

@ -24134,7 +24134,7 @@
"deprecation_date": "2027-07-21",
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 1.5e-08,
"cache_read_input_token_cost_priority": 5e-08,
"cache_read_input_token_cost_priority": 5.4e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,
@ -47858,7 +47858,7 @@
"deprecation_date": "2027-07-21",
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 1.5e-08,
"cache_read_input_token_cost_priority": 5e-08,
"cache_read_input_token_cost_priority": 5.4e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,

2
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -4560,7 +4560,7 @@ GEMINI_35_FLASH_LITE_TIER_RATES_BY_SURFACE = [
("gemini", "priority", 5.4e-07, 4.5e-06, 5e-08),
("vertex_ai", None, 3e-07, 2.5e-06, 3e-08),
("vertex_ai", "flex", 1.5e-07, 1.25e-06, 1.5e-08),
("vertex_ai", "priority", 5.4e-07, 4.5e-06, 5e-08),
("vertex_ai", "priority", 5.4e-07, 4.5e-06, 5.4e-08),
]