diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 06b6411af2..dcda02f694 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -12297,7 +12297,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
         "input_cost_per_token": 2.5e-8,
@@ -12305,7 +12307,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
         "input_cost_per_token": 9e-8,
@@ -12313,7 +12317,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
         "input_cost_per_token": 2e-7,
@@ -12321,7 +12327,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
         "input_cost_per_token": 7e-8,
@@ -12329,7 +12337,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
         "input_cost_per_token": 1.5e-7,
@@ -12337,7 +12347,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/mistralai/mixtral-8x22b-instruct-v0.1": {
         "input_cost_per_token": 6e-7,
@@ -12345,7 +12357,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/meta-llama/Llama-3.1-8B-Instruct": {
         "input_cost_per_token": 3e-8,
@@ -12353,7 +12367,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/meta-llama/Llama-3.3-70B-Instruct": {
         "input_cost_per_token": 2e-7,
@@ -12361,7 +12377,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/black-forest-labs/FLUX.1-schnell": {
         "mode": "image_generation",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 06b6411af2..dcda02f694 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -12297,7 +12297,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.75/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Llama-8B": {
         "input_cost_per_token": 2.5e-8,
@@ -12305,7 +12307,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.05/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
         "input_cost_per_token": 9e-8,
@@ -12313,7 +12317,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.18/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B": {
         "input_cost_per_token": 2e-7,
@@ -12321,7 +12327,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
         "input_cost_per_token": 7e-8,
@@ -12329,7 +12337,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.14/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B": {
         "input_cost_per_token": 1.5e-7,
@@ -12337,7 +12347,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.30/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/mistralai/mixtral-8x22b-instruct-v0.1": {
         "input_cost_per_token": 6e-7,
@@ -12345,7 +12357,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $1.20/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/meta-llama/Llama-3.1-8B-Instruct": {
         "input_cost_per_token": 3e-8,
@@ -12353,7 +12367,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.06/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/meta-llama/Llama-3.3-70B-Instruct": {
         "input_cost_per_token": 2e-7,
@@ -12361,7 +12377,9 @@
         "litellm_provider": "nscale",
         "mode": "chat",
         "source": "https://docs.nscale.com/docs/inference/serverless-models/current#chat-models",
-        "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        "metadata": {
+            "notes": "Pricing listed as $0.40/1M tokens total. Assumed 50/50 split for input/output."
+        }
     },
     "nscale/black-forest-labs/FLUX.1-schnell": {
         "mode": "image_generation",