From 14e4b9f906c5ca3ef6f256ed622688ee55076c0c Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 17 Sep 2026 19:14:04 +0000 Subject: [PATCH] fix(gemini): 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 | 2 +- model_prices_and_context_window.json | 2 +- .../llm_cost_calc/test_llm_cost_calc_utils.py | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a39017f0ab9..5fd860a040c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -27838,7 +27838,7 @@ "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 2e-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 a39017f0ab9..5fd860a040c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -27838,7 +27838,7 @@ "gemini/gemini-3.5-flash-lite": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_flex": 2e-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 798d657cce7..a285d5431b7 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 @@ -3426,7 +3426,7 @@ GEMINI_36_FLASH_SERVICE_TIER_PRICING = [ GEMINI_35_FLASH_LITE_TIER_RATES_BY_SURFACE = [ ("gemini", None, 3e-07, 2.5e-06, 3e-08), ("gemini", "flex", 1.5e-07, 1.25e-06, 2e-08), - ("gemini", "priority", 5.4e-07, 4.5e-06, 5e-08), + ("gemini", "priority", 5.4e-07, 4.5e-06, 5.4e-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, 5.4e-08),