diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 81b5c690be..4a627d4aa1 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -18749,13 +18749,27 @@
     },
     "gpt-5.4-mini": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "cache_read_input_token_cost_flex": 3.9e-08,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
         "input_cost_per_token": 7.5e-07,
+        "input_cost_per_token_above_272k_tokens": 1.5e-06,
+        "input_cost_per_token_flex": 3.75e-07,
+        "input_cost_per_token_batches": 3.75e-07,
+        "input_cost_per_token_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
+        "output_cost_per_token_above_272k_tokens": 6.75e-06,
+        "output_cost_per_token_flex": 2.25e-06,
+        "output_cost_per_token_batches": 2.25e-06,
+        "output_cost_per_token_priority": 6.75e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.0125e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -18777,19 +18791,34 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": true,
         "supports_xhigh_reasoning_effort": true
     },
     "gpt-5.4-nano": {
         "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
+        "cache_read_input_token_cost_flex": 1.04e-08,
+        "cache_read_input_token_cost_priority": 4e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-07,
+        "input_cost_per_token_flex": 1e-07,
+        "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_flex": 6.25e-07,
+        "output_cost_per_token_batches": 6.25e-07,
+        "output_cost_per_token_priority": 1.875e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 2.8125e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -18811,6 +18840,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": false,
         "supports_xhigh_reasoning_effort": true
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 81b5c690be..4a627d4aa1 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -18749,13 +18749,27 @@
     },
     "gpt-5.4-mini": {
         "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "cache_read_input_token_cost_flex": 3.9e-08,
+        "cache_read_input_token_cost_priority": 1.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
         "input_cost_per_token": 7.5e-07,
+        "input_cost_per_token_above_272k_tokens": 1.5e-06,
+        "input_cost_per_token_flex": 3.75e-07,
+        "input_cost_per_token_batches": 3.75e-07,
+        "input_cost_per_token_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.5e-06,
+        "output_cost_per_token_above_272k_tokens": 6.75e-06,
+        "output_cost_per_token_flex": 2.25e-06,
+        "output_cost_per_token_batches": 2.25e-06,
+        "output_cost_per_token_priority": 6.75e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.0125e-05,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -18777,19 +18791,34 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": true,
         "supports_xhigh_reasoning_effort": true
     },
     "gpt-5.4-nano": {
         "cache_read_input_token_cost": 2e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 4e-08,
+        "cache_read_input_token_cost_flex": 1.04e-08,
+        "cache_read_input_token_cost_priority": 4e-08,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_above_272k_tokens": 4e-07,
+        "input_cost_per_token_flex": 1e-07,
+        "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_flex": 6.25e-07,
+        "output_cost_per_token_batches": 6.25e-07,
+        "output_cost_per_token_priority": 1.875e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 2.8125e-06,
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -18811,6 +18840,7 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
+        "supports_service_tier": true,
         "supports_vision": true,
         "supports_none_reasoning_effort": false,
         "supports_xhigh_reasoning_effort": true