From 3acdfda19c37b88d2011982d3fb6d5850ce43d49 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 24 Sep 2026 06:52:06 -0700 Subject: [PATCH] fix(cost-map): add batch prices for vertex gemini-3.8-flash-cyber (#42953) Co-authored-by: kerry Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 6 ++++++ model_prices_and_context_window.json | 6 ++++++ 2 files changed, 12 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index a1878c00678..b5282f12539 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -27350,9 +27350,11 @@ }, "vertex_ai/gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai", @@ -27362,6 +27364,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "regional_endpoint_uplift_multiplier": 1.1, @@ -29604,9 +29607,11 @@ }, "gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", @@ -29616,6 +29621,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index a1878c00678..b5282f12539 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -27350,9 +27350,11 @@ }, "vertex_ai/gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai", @@ -27362,6 +27364,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "regional_endpoint_uplift_multiplier": 1.1, @@ -29604,9 +29607,11 @@ }, "gemini-3.8-flash-cyber": { "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost_batches": 7.5e-08, "cache_read_input_token_cost_flex": 7.5e-08, "cache_read_input_token_cost_priority": 2.7e-07, "input_cost_per_token": 1.5e-06, + "input_cost_per_token_batches": 7.5e-07, "input_cost_per_token_flex": 7.5e-07, "input_cost_per_token_priority": 2.7e-06, "litellm_provider": "vertex_ai-language-models", @@ -29616,6 +29621,7 @@ "mode": "chat", "output_cost_per_reasoning_token": 7.5e-06, "output_cost_per_token": 7.5e-06, + "output_cost_per_token_batches": 3.75e-06, "output_cost_per_token_flex": 3.75e-06, "output_cost_per_token_priority": 1.35e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",