From acab4761a210cd883653c04083925c9d927d6747 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, 8 Oct 2026 17:23:42 -0700
Subject: [PATCH] fix(cost-map): update baseten DeepSeek-V4.1-Flash-Fast cache
 read price and max output (#45468)

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 bbd0d9ab989..3b2e0af5f49 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -80491,12 +80491,12 @@
         "supports_web_search": true
     },
     "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": {
-        "cache_read_input_token_cost": 1.4e-07,
+        "cache_read_input_token_cost": 1.4e-08,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "max_input_tokens": 1048576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
         "source": "https://inference.baseten.co/v1/models",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index bbd0d9ab989..3b2e0af5f49 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -80491,12 +80491,12 @@
         "supports_web_search": true
     },
     "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": {
-        "cache_read_input_token_cost": 1.4e-07,
+        "cache_read_input_token_cost": 1.4e-08,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "baseten",
         "max_input_tokens": 1048576,
-        "max_output_tokens": 32768,
-        "max_tokens": 32768,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
         "source": "https://inference.baseten.co/v1/models",