diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 877df1bb78..1d12d1a74a 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -2004,9 +2004,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [
@@ -12830,9 +12830,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 877df1bb78..1d12d1a74a 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -2004,9 +2004,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [
@@ -12830,9 +12830,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
-        "max_output_tokens": 128000,
-        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "supported_endpoints": [