From a053bf2a5c06059eda6ff09a00dac5da7e9ca0b6 Mon Sep 17 00:00:00 2001
From: "devin-ai-integration[bot]"
 <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Tue, 10 Nov 2026 00:34:19 +0000
Subject: [PATCH] fix(cost-map): price wandb DeepSeek-V4.1-Flash-1017 from the
 CoreWeave Forge listing (#50776)

Co-authored-by: devin-ai-integration[bot] <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, 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 6c1f41b2545..68bbf612e31 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -87346,13 +87346,13 @@
         "supports_vision": true
     },
     "wandb/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
-        "cache_read_input_token_cost": 2e-09,
-        "input_cost_per_token": 1.3e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "max_output_tokens": 1048576,
         "mode": "chat",
-        "output_cost_per_token": 6.5e-07,
+        "output_cost_per_token": 1.2e-06,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_prompt_caching": true,
         "supports_reasoning": true,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 6c1f41b2545..68bbf612e31 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -87346,13 +87346,13 @@
         "supports_vision": true
     },
     "wandb/deepseek-ai/DeepSeek-V4.1-Flash-1017": {
-        "cache_read_input_token_cost": 2e-09,
-        "input_cost_per_token": 1.3e-07,
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "max_output_tokens": 1048576,
         "mode": "chat",
-        "output_cost_per_token": 6.5e-07,
+        "output_cost_per_token": 1.2e-06,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_prompt_caching": true,
         "supports_reasoning": true,