diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 0b97d8761fc..6d814c731dc 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -1644,7 +1644,7 @@
         "cache_read_input_token_cost": 1.4e-07,
         "input_cost_per_token": 1.38e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -1944,7 +1944,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -2893,7 +2893,7 @@
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -2964,7 +2964,7 @@
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -2997,7 +2997,7 @@
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -3092,9 +3092,9 @@
         "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,
         "source": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/",
@@ -3377,7 +3377,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -3440,7 +3440,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -3500,7 +3500,7 @@
         "cache_read_input_token_cost": 1.75e-07,
         "input_cost_per_token": 1.75e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -3637,7 +3637,7 @@
     "azure/gpt-5.2-pro": {
         "input_cost_per_token": 2.1e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -3668,7 +3668,7 @@
     "azure/gpt-5.2-pro-2025-12-11": {
         "input_cost_per_token": 2.1e-05,
         "litellm_provider": "azure",
-        "max_input_tokens": 400000,
+        "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -4684,7 +4684,7 @@
         "cache_read_input_token_cost": 1.4e-07,
         "input_cost_per_token": 1.38e-06,
         "litellm_provider": "azure",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 128000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -17470,7 +17470,7 @@
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -17507,7 +17507,7 @@
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -17543,7 +17543,7 @@
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -17852,7 +17852,7 @@
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -17887,9 +17887,9 @@
         "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": [
@@ -17951,7 +17951,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -17983,7 +17983,7 @@
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -18046,7 +18046,7 @@
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
@@ -18081,7 +18081,7 @@
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -18120,7 +18120,7 @@
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -18158,7 +18158,7 @@
         "input_cost_per_token_flex": 2.5e-08,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -18193,7 +18193,7 @@
         "input_cost_per_token": 5e-08,
         "input_cost_per_token_flex": 2.5e-08,
         "litellm_provider": "openai",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -23206,9 +23206,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openrouter",
-        "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_modalities": [
@@ -23225,7 +23225,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -23244,7 +23244,7 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -23263,7 +23263,7 @@
         "cache_read_input_token_cost": 2.5e-08,
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
@@ -23282,7 +23282,7 @@
         "cache_read_input_token_cost": 5e-09,
         "input_cost_per_token": 5e-08,
         "litellm_provider": "openrouter",
-        "max_input_tokens": 272000,
+        "max_input_tokens": 400000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",