diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 91704142474..d9a13ef1b98 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -6592,6 +6592,10 @@
         "supports_web_search": true
     },
     "azure/gpt-5.6": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
+        "cache_creation_input_token_cost_priority": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
         "cache_read_input_token_cost_priority": 1e-06,
@@ -6642,6 +6646,10 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
+        "cache_creation_input_token_cost_priority": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
         "cache_read_input_token_cost_priority": 1e-06,
@@ -6693,6 +6701,10 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_priority": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
         "cache_read_input_token_cost_priority": 4e-07,
@@ -6744,6 +6756,10 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_creation_input_token_cost_priority": 5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
         "cache_read_input_token_cost": 2e-08,
         "cache_read_input_token_cost_above_272k_tokens": 4e-08,
         "cache_read_input_token_cost_priority": 4e-08,
@@ -6795,12 +6811,18 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6808,7 +6830,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6842,13 +6865,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6856,7 +6885,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6890,13 +6920,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
-        "cache_read_input_token_cost_priority": 5.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
-        "input_cost_per_token_priority": 5.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6904,7 +6940,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-05,
         "output_cost_per_token_above_272k_tokens": 1.98e-05,
-        "output_cost_per_token_priority": 3.3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
+        "output_cost_per_token_priority": 2.64e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6938,13 +6975,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.75e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
+        "cache_creation_input_token_cost_priority": 5.5e-07,
         "cache_read_input_token_cost": 2.2e-08,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
-        "cache_read_input_token_cost_priority": 5.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
+        "cache_read_input_token_cost_priority": 4.4e-08,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
-        "input_cost_per_token_priority": 5.5e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
+        "input_cost_per_token_priority": 4.4e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6952,7 +6995,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-06,
         "output_cost_per_token_above_272k_tokens": 1.98e-06,
-        "output_cost_per_token_priority": 3.3e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
+        "output_cost_per_token_priority": 2.64e-06,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6986,12 +7030,18 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6999,7 +7049,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -7033,13 +7084,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -7047,7 +7104,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -7081,13 +7139,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
-        "cache_read_input_token_cost_priority": 5.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
-        "input_cost_per_token_priority": 5.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -7095,7 +7159,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-05,
         "output_cost_per_token_above_272k_tokens": 1.98e-05,
-        "output_cost_per_token_priority": 3.3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
+        "output_cost_per_token_priority": 2.64e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -7129,13 +7194,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.75e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
+        "cache_creation_input_token_cost_priority": 5.5e-07,
         "cache_read_input_token_cost": 2.2e-08,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
-        "cache_read_input_token_cost_priority": 5.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
+        "cache_read_input_token_cost_priority": 4.4e-08,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
-        "input_cost_per_token_priority": 5.5e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
+        "input_cost_per_token_priority": 4.4e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -7143,7 +7214,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-06,
         "output_cost_per_token_above_272k_tokens": 1.98e-06,
-        "output_cost_per_token_priority": 3.3e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
+        "output_cost_per_token_priority": 2.64e-06,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 91704142474..d9a13ef1b98 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -6592,6 +6592,10 @@
         "supports_web_search": true
     },
     "azure/gpt-5.6": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
+        "cache_creation_input_token_cost_priority": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
         "cache_read_input_token_cost_priority": 1e-06,
@@ -6642,6 +6646,10 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 6.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
+        "cache_creation_input_token_cost_priority": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05,
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
         "cache_read_input_token_cost_priority": 1e-06,
@@ -6693,6 +6701,10 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-06,
+        "cache_creation_input_token_cost_priority": 5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
         "cache_read_input_token_cost": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
         "cache_read_input_token_cost_priority": 4e-07,
@@ -6744,6 +6756,10 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_creation_input_token_cost_priority": 5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
         "cache_read_input_token_cost": 2e-08,
         "cache_read_input_token_cost_above_272k_tokens": 4e-08,
         "cache_read_input_token_cost_priority": 4e-08,
@@ -6795,12 +6811,18 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6808,7 +6830,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6842,13 +6865,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6856,7 +6885,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6890,13 +6920,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
-        "cache_read_input_token_cost_priority": 5.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
-        "input_cost_per_token_priority": 5.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6904,7 +6940,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-05,
         "output_cost_per_token_above_272k_tokens": 1.98e-05,
-        "output_cost_per_token_priority": 3.3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
+        "output_cost_per_token_priority": 2.64e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6938,13 +6975,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/us/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.75e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
+        "cache_creation_input_token_cost_priority": 5.5e-07,
         "cache_read_input_token_cost": 2.2e-08,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
-        "cache_read_input_token_cost_priority": 5.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
+        "cache_read_input_token_cost_priority": 4.4e-08,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
-        "input_cost_per_token_priority": 5.5e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
+        "input_cost_per_token_priority": 4.4e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6952,7 +6995,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-06,
         "output_cost_per_token_above_272k_tokens": 1.98e-06,
-        "output_cost_per_token_priority": 3.3e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
+        "output_cost_per_token_priority": 2.64e-06,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -6986,12 +7030,18 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -6999,7 +7049,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -7033,13 +7084,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-sol": {
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05,
+        "cache_creation_input_token_cost_priority": 1.375e-05,
         "cache_read_input_token_cost": 5.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
-        "cache_read_input_token_cost_priority": 1.375e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06,
+        "cache_read_input_token_cost_priority": 1.1e-06,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
-        "input_cost_per_token_priority": 1.375e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 2.2e-05,
+        "input_cost_per_token_priority": 1.1e-05,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -7047,7 +7104,8 @@
         "mode": "chat",
         "output_cost_per_token": 3.3e-05,
         "output_cost_per_token_above_272k_tokens": 4.95e-05,
-        "output_cost_per_token_priority": 8.25e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 9.9e-05,
+        "output_cost_per_token_priority": 6.6e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -7081,13 +7139,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-terra": {
+        "cache_creation_input_token_cost": 2.75e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-05,
+        "cache_creation_input_token_cost_priority": 5.5e-06,
         "cache_read_input_token_cost": 2.2e-07,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-07,
-        "cache_read_input_token_cost_priority": 5.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-07,
+        "cache_read_input_token_cost_priority": 4.4e-07,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-06,
         "input_cost_per_token_above_272k_tokens": 4.4e-06,
-        "input_cost_per_token_priority": 5.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-06,
+        "input_cost_per_token_priority": 4.4e-06,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -7095,7 +7159,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-05,
         "output_cost_per_token_above_272k_tokens": 1.98e-05,
-        "output_cost_per_token_priority": 3.3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-05,
+        "output_cost_per_token_priority": 2.64e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
@@ -7129,13 +7194,19 @@
         "supports_minimal_reasoning_effort": false
     },
     "azure/eu/gpt-5.6-luna": {
+        "cache_creation_input_token_cost": 2.75e-07,
+        "cache_creation_input_token_cost_above_272k_tokens": 5.5e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_priority": 1.1e-06,
+        "cache_creation_input_token_cost_priority": 5.5e-07,
         "cache_read_input_token_cost": 2.2e-08,
         "cache_read_input_token_cost_above_272k_tokens": 4.4e-08,
-        "cache_read_input_token_cost_priority": 5.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8.8e-08,
+        "cache_read_input_token_cost_priority": 4.4e-08,
         "deprecation_date": "2028-01-11",
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
-        "input_cost_per_token_priority": 5.5e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8.8e-07,
+        "input_cost_per_token_priority": 4.4e-07,
         "litellm_provider": "azure",
         "max_input_tokens": 922000,
         "max_output_tokens": 128000,
@@ -7143,7 +7214,8 @@
         "mode": "chat",
         "output_cost_per_token": 1.32e-06,
         "output_cost_per_token_above_272k_tokens": 1.98e-06,
-        "output_cost_per_token_priority": 3.3e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.96e-06,
+        "output_cost_per_token_priority": 2.64e-06,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json
index f7f60c7666d..4eee9d52bc7 100644
--- a/model_prices_and_context_window.schema.json
+++ b/model_prices_and_context_window.schema.json
@@ -104,6 +104,11 @@
           "minimum": 0,
           "description": "Flex service-tier rate for the same-named base field."
         },
+        "cache_creation_input_token_cost_above_272k_tokens_priority": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Priority service-tier rate for the same-named base field."
+        },
         "cache_creation_input_token_cost_flex": {
           "type": "number",
           "minimum": 0,
diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py
index 304ce16b0ed..82ab3b3bd08 100644
--- a/tests/test_litellm/test_cost_calculator.py
+++ b/tests/test_litellm/test_cost_calculator.py
@@ -1727,6 +1727,73 @@ def test_azure_ai_cache_cost_calculation(_local_model_cost_map):
     ), f"Output cost mismatch: got {output_cost}, expected {expected_output_cost}"
 
 
+
+AZURE_GPT_5_6_MAP_KEYS = (
+    "azure/gpt-5.6",
+    "azure/gpt-5.6-sol",
+    "azure/gpt-5.6-terra",
+    "azure/gpt-5.6-luna",
+    "azure/us/gpt-5.6",
+    "azure/us/gpt-5.6-sol",
+    "azure/us/gpt-5.6-terra",
+    "azure/us/gpt-5.6-luna",
+    "azure/eu/gpt-5.6",
+    "azure/eu/gpt-5.6-sol",
+    "azure/eu/gpt-5.6-terra",
+    "azure/eu/gpt-5.6-luna",
+)
+
+
+def test_azure_gpt_5_6_cache_write_tokens_are_billed(_local_model_cost_map):
+    """
+    Azure bills gpt-5.6 prompt cache writes at 1.25x the input rate on every
+    tier, but the azure entries carried no ``cache_creation_input_token_cost``,
+    so cache-write tokens were billed at the plain input rate instead.
+    """
+    from litellm.litellm_core_utils.llm_cost_calc.utils import generic_cost_per_token
+    from litellm.types.utils import PromptTokensDetailsWrapper, Usage
+
+    usage = Usage(
+        completion_tokens=100,
+        prompt_tokens=2000,
+        total_tokens=2100,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=0, text_tokens=687),
+        cache_creation_input_tokens=1313,
+    )
+
+    input_cost, output_cost = generic_cost_per_token(
+        model="azure/gpt-5.6-luna", usage=usage, custom_llm_provider="azure"
+    )
+
+    assert input_cost == pytest.approx(687 * 2e-07 + 1313 * 2.5e-07)
+    assert output_cost == pytest.approx(100 * 1.2e-06)
+
+
+@pytest.mark.parametrize("model", AZURE_GPT_5_6_MAP_KEYS)
+def test_azure_gpt_5_6_rates_match_azure_price_page(_local_model_cost_map, model):
+    """
+    Per the Azure OpenAI price page (rendered 2026-08-26): cache writes cost
+    1.25x input on every gpt-5.6 tier, and Data Zone costs 1.1x Global for
+    standard and priority alike (us/eu priority rates previously sat at 1.25x).
+    """
+    entry = litellm.model_cost[model]
+    input_keys = [key for key in entry if key.startswith("input_cost_per_token")]
+    assert input_keys
+    for key in input_keys:
+        suffix = key[len("input_cost_per_token") :]
+        assert entry["cache_creation_input_token_cost" + suffix] == pytest.approx(entry[key] * 1.25)
+
+    zone = model.split("/")[1]
+    if zone in ("us", "eu"):
+        global_entry = litellm.model_cost["azure/" + model.split("/", 2)[2]]
+        prefixes = ("input_cost_per_token", "output_cost_per_token", "cache_read", "cache_creation")
+        token_cost_keys = [key for key in entry if key.startswith(prefixes)]
+        global_token_cost_keys = [key for key in global_entry if key.startswith(prefixes)]
+        assert len(token_cost_keys) >= 9
+        assert sorted(token_cost_keys) == sorted(global_token_cost_keys)
+        for key in token_cost_keys:
+            assert entry[key] == pytest.approx(global_entry[key] * 1.1), key
+
 def test_vertex_regional_deployment_costs_uplift_over_global(monkeypatch):
     """
     Regression for https://github.com/BerriAI/litellm/issues/34393: two Vertex
diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py
index e1ea6edb2d8..f0d9e62f6f8 100644
--- a/tests/test_litellm/test_utils.py
+++ b/tests/test_litellm/test_utils.py
@@ -845,6 +845,9 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "cache_creation_input_token_cost_above_272k_tokens_flex": {
                     "type": "number"
                 },
+                "cache_creation_input_token_cost_above_272k_tokens_priority": {
+                    "type": "number"
+                },
                 "cache_creation_input_token_cost_flex": {"type": "number"},
                 "cache_creation_input_token_cost_priority": {"type": "number"},
                 "cache_read_input_token_cost": {"type": "number"},