From 18d85c72030e39f505d464f0709043986a38ddbb Mon Sep 17 00:00:00 2001
From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Mon, 14 Sep 2026 22:14:56 +0000
Subject: [PATCH] fix(cost_map): vertex gemini-3.5-flash-lite priority cache
 read is $0.054/M

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 litellm/model_prices_and_context_window_backup.json           | 4 ++--
 model_prices_and_context_window.json                          | 4 ++--
 .../llm_cost_calc/test_llm_cost_calc_utils.py                 | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 685e63dcc56..35b5a4ceb6e 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -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,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 685e63dcc56..35b5a4ceb6e 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -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,
diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index 2fadb1fd959..2289de9a951 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -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),
 ]