From d387cdc81628d127657bebda4024d19fd83ee7e6 Mon Sep 17 00:00:00 2001
From: "berriai-litellm-provider-info-sync[bot]"
 <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
Date: Thu, 15 Oct 2026 17:23:57 -0700
Subject: [PATCH] fix(vertex-ai): end free period for deepseek-v4.1-flash-maas
 (#46793)

Price-Sync: litellm-providers

Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com>
---
 litellm/model_prices_and_context_window_backup.json | 6 +++---
 model_prices_and_context_window.json                | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 308dfdeb62a..6f0630dd01b 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -75076,14 +75076,14 @@
         "supports_vision": true
     },
     "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": {
-        "cache_read_input_token_cost": 0.0,
-        "input_cost_per_token": 0.0,
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "vertex_ai-deepseek_models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
-        "output_cost_per_token": 0.0,
+        "output_cost_per_token": 1.2e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_regions": [
             "global"
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 308dfdeb62a..6f0630dd01b 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -75076,14 +75076,14 @@
         "supports_vision": true
     },
     "vertex_ai/deepseek-ai/deepseek-v4.1-flash-maas": {
-        "cache_read_input_token_cost": 0.0,
-        "input_cost_per_token": 0.0,
+        "cache_read_input_token_cost": 3e-08,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "vertex_ai-deepseek_models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
-        "output_cost_per_token": 0.0,
+        "output_cost_per_token": 1.2e-06,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_regions": [
             "global"