diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 84609da226f..45c2bfa2893 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -55086,14 +55086,16 @@
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/deepseek-ai/DeepSeek-V3.1": {
+        "cache_read_input_token_cost": 2e-07,
         "supports_reasoning": true,
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
-        "input_cost_per_token": 5.5e-07,
-        "output_cost_per_token": 1.65e-06,
+        "input_cost_per_token": 5e-07,
+        "output_cost_per_token": 1.5e-06,
         "litellm_provider": "wandb",
         "mode": "chat",
-        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
+        "supports_prompt_caching": true
     },
     "wandb/meta-llama/Llama-3.3-70B-Instruct": {
         "max_input_tokens": 128000,
@@ -66502,13 +66504,13 @@
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
         "input_cost_per_token": 1.3e-07,
-        "output_cost_per_token": 2.8e-07,
-        "cache_read_input_token_cost": 7e-08,
+        "output_cost_per_token": 2.7e-07,
+        "cache_read_input_token_cost": 5e-08,
         "supports_prompt_caching": true,
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_vision": false,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/deepseek-ai/DeepSeek-V4-Pro": {
         "supports_reasoning": true,
@@ -66585,14 +66587,14 @@
         "supports_reasoning": true,
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
-        "input_cost_per_token": 7.1e-07,
-        "output_cost_per_token": 3.5e-06,
-        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 3e-06,
+        "cache_read_input_token_cost": 1.2e-07,
         "supports_prompt_caching": true,
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_vision": true,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/moonshotai/Kimi-K2.6": {
         "supports_reasoning": true,
@@ -66658,15 +66660,17 @@
         "source": "https://wandb.ai/site/pricing/tokens/"
     },
     "wandb/Qwen/Qwen3.6-35B-A3B": {
+        "cache_read_input_token_cost": 3.5e-08,
         "supports_reasoning": true,
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
-        "input_cost_per_token": 2.5e-07,
-        "output_cost_per_token": 1.25e-06,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 8.9e-07,
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_vision": true,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
+        "supports_prompt_caching": true
     },
     "wandb/Qwen/Qwen3.6-27B": {
         "supports_reasoning": true,
@@ -66720,18 +66724,18 @@
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_reasoning": true,
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_token": 6e-08,
         "output_cost_per_token": 1.5e-07,
-        "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost": 1.5e-08,
         "max_input_tokens": 131000,
         "supports_prompt_caching": true,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/zai-org/GLM-5.2": {
         "supports_reasoning": true,
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
-        "input_cost_per_token": 7.6e-07,
+        "input_cost_per_token": 6.2e-07,
         "output_cost_per_token": 2.42e-06,
         "cache_read_input_token_cost": 1.4e-07,
         "supports_prompt_caching": true,
@@ -74287,14 +74291,14 @@
         ]
     },
     "wandb/deepseek-ai/DeepSeek-V4.1-Flash": {
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-09,
+        "input_cost_per_token": 1.3e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "max_output_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.5e-07,
-        "source": "https://wandb.ai/site/pricing/tokens/",
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_vision": true
@@ -74315,13 +74319,13 @@
         "supports_vision": true
     },
     "wandb/zai-org/GLM-5.3-Flash": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 1.5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.2e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://docs.wandb.ai/inference/models.md",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -78687,13 +78691,13 @@
         "supports_vision": true
     },
     "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 2.5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "max_output_tokens": 943718,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 5e-07,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -78989,12 +78993,12 @@
         "supports_vision": true
     },
     "wandb/reflection/Beam-1.0-501B-A23B": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "mode": "chat",
-        "output_cost_per_token": 3e-06,
+        "output_cost_per_token": 1e-06,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -79005,11 +79009,11 @@
     },
     "wandb/zai-org/GLM-5.3": {
         "cache_read_input_token_cost": 1.9e-07,
-        "input_cost_per_token": 1.2e-06,
+        "input_cost_per_token": 7.5e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "mode": "chat",
-        "output_cost_per_token": 4e-06,
+        "output_cost_per_token": 3e-06,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -86862,5 +86866,18 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "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,
+        "litellm_provider": "wandb",
+        "max_input_tokens": 1049000,
+        "max_output_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 6.5e-07,
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true
     }
 }
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 84609da226f..45c2bfa2893 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -55086,14 +55086,16 @@
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/deepseek-ai/DeepSeek-V3.1": {
+        "cache_read_input_token_cost": 2e-07,
         "supports_reasoning": true,
         "max_input_tokens": 128000,
         "max_output_tokens": 128000,
-        "input_cost_per_token": 5.5e-07,
-        "output_cost_per_token": 1.65e-06,
+        "input_cost_per_token": 5e-07,
+        "output_cost_per_token": 1.5e-06,
         "litellm_provider": "wandb",
         "mode": "chat",
-        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
+        "supports_prompt_caching": true
     },
     "wandb/meta-llama/Llama-3.3-70B-Instruct": {
         "max_input_tokens": 128000,
@@ -66502,13 +66504,13 @@
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
         "input_cost_per_token": 1.3e-07,
-        "output_cost_per_token": 2.8e-07,
-        "cache_read_input_token_cost": 7e-08,
+        "output_cost_per_token": 2.7e-07,
+        "cache_read_input_token_cost": 5e-08,
         "supports_prompt_caching": true,
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_vision": false,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/deepseek-ai/DeepSeek-V4-Pro": {
         "supports_reasoning": true,
@@ -66585,14 +66587,14 @@
         "supports_reasoning": true,
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
-        "input_cost_per_token": 7.1e-07,
-        "output_cost_per_token": 3.5e-06,
-        "cache_read_input_token_cost": 1.5e-07,
+        "input_cost_per_token": 6e-07,
+        "output_cost_per_token": 3e-06,
+        "cache_read_input_token_cost": 1.2e-07,
         "supports_prompt_caching": true,
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_vision": true,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/moonshotai/Kimi-K2.6": {
         "supports_reasoning": true,
@@ -66658,15 +66660,17 @@
         "source": "https://wandb.ai/site/pricing/tokens/"
     },
     "wandb/Qwen/Qwen3.6-35B-A3B": {
+        "cache_read_input_token_cost": 3.5e-08,
         "supports_reasoning": true,
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
-        "input_cost_per_token": 2.5e-07,
-        "output_cost_per_token": 1.25e-06,
+        "input_cost_per_token": 1e-07,
+        "output_cost_per_token": 8.9e-07,
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_vision": true,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
+        "supports_prompt_caching": true
     },
     "wandb/Qwen/Qwen3.6-27B": {
         "supports_reasoning": true,
@@ -66720,18 +66724,18 @@
         "litellm_provider": "wandb",
         "mode": "chat",
         "supports_reasoning": true,
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_token": 6e-08,
         "output_cost_per_token": 1.5e-07,
-        "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost": 1.5e-08,
         "max_input_tokens": 131000,
         "supports_prompt_caching": true,
-        "source": "https://wandb.ai/site/pricing/tokens/"
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference"
     },
     "wandb/zai-org/GLM-5.2": {
         "supports_reasoning": true,
         "max_output_tokens": 262144,
         "max_input_tokens": 262000,
-        "input_cost_per_token": 7.6e-07,
+        "input_cost_per_token": 6.2e-07,
         "output_cost_per_token": 2.42e-06,
         "cache_read_input_token_cost": 1.4e-07,
         "supports_prompt_caching": true,
@@ -74287,14 +74291,14 @@
         ]
     },
     "wandb/deepseek-ai/DeepSeek-V4.1-Flash": {
-        "cache_read_input_token_cost": 3e-08,
-        "input_cost_per_token": 2e-07,
+        "cache_read_input_token_cost": 2e-09,
+        "input_cost_per_token": 1.3e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "max_output_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.5e-07,
-        "source": "https://wandb.ai/site/pricing/tokens/",
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_vision": true
@@ -74315,13 +74319,13 @@
         "supports_vision": true
     },
     "wandb/zai-org/GLM-5.3-Flash": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 1.5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.2e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "mode": "chat",
-        "output_cost_per_token": 5e-07,
-        "source": "https://docs.wandb.ai/inference/models.md",
+        "output_cost_per_token": 3.8e-07,
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -78687,13 +78691,13 @@
         "supports_vision": true
     },
     "wandb/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B": {
-        "cache_read_input_token_cost": 5e-08,
-        "input_cost_per_token": 2.5e-07,
+        "cache_read_input_token_cost": 2e-08,
+        "input_cost_per_token": 1.5e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "max_output_tokens": 943718,
         "mode": "chat",
-        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token": 5e-07,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -78989,12 +78993,12 @@
         "supports_vision": true
     },
     "wandb/reflection/Beam-1.0-501B-A23B": {
-        "cache_read_input_token_cost": 1e-07,
-        "input_cost_per_token": 1e-06,
+        "cache_read_input_token_cost": 4e-08,
+        "input_cost_per_token": 3e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "mode": "chat",
-        "output_cost_per_token": 3e-06,
+        "output_cost_per_token": 1e-06,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -79005,11 +79009,11 @@
     },
     "wandb/zai-org/GLM-5.3": {
         "cache_read_input_token_cost": 1.9e-07,
-        "input_cost_per_token": 1.2e-06,
+        "input_cost_per_token": 7.5e-07,
         "litellm_provider": "wandb",
         "max_input_tokens": 1049000,
         "mode": "chat",
-        "output_cost_per_token": 4e-06,
+        "output_cost_per_token": 3e-06,
         "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
@@ -86862,5 +86866,18 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "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,
+        "litellm_provider": "wandb",
+        "max_input_tokens": 1049000,
+        "max_output_tokens": 1048576,
+        "mode": "chat",
+        "output_cost_per_token": 6.5e-07,
+        "source": "https://www.coreweave.com/products/coreweave-forge/serverless-inference",
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true
     }
 }