diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 543172b838..fb5bfa6cf4 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -2112,6 +2112,380 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "azure_ai/gpt-5.4": {
+        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_priority": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "input_cost_per_token_priority": 5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "output_cost_per_token_priority": 3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/gpt-5.4-2026-03-05": {
+        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_priority": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "input_cost_per_token_priority": 5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "output_cost_per_token_priority": 3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/gpt-5.4-pro": {
+        "cache_read_input_token_cost": 3e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
+        "input_cost_per_token": 3e-05,
+        "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 0.00018,
+        "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/gpt-5.4-pro-2026-03-05": {
+        "cache_read_input_token_cost": 3e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
+        "input_cost_per_token": 3e-05,
+        "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 0.00018,
+        "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/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_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_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "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_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
+    "azure_ai/gpt-5.4-mini-2026-03-17": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "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_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "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_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
+    "azure_ai/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_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_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
+    "azure_ai/gpt-5.4-nano-2026-03-17": {
+        "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,
+        "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_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
     "azure_ai/model_router": {
         "input_cost_per_token": 1.4e-07,
         "output_cost_per_token": 0,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 3eabb82093..94f0f1e78d 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -2141,6 +2141,380 @@
         "supports_response_schema": true,
         "supports_tool_choice": true
     },
+    "azure_ai/gpt-5.4": {
+        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_priority": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "input_cost_per_token_priority": 5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "output_cost_per_token_priority": 3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/gpt-5.4-2026-03-05": {
+        "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_priority": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
+        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens": 5e-06,
+        "input_cost_per_token_priority": 5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 1e-05,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens": 2.25e-05,
+        "output_cost_per_token_priority": 3e-05,
+        "output_cost_per_token_above_272k_tokens_priority": 4.5e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/gpt-5.4-pro": {
+        "cache_read_input_token_cost": 3e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
+        "input_cost_per_token": 3e-05,
+        "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 0.00018,
+        "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/gpt-5.4-pro-2026-03-05": {
+        "cache_read_input_token_cost": 3e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 6e-06,
+        "cache_read_input_token_cost_priority": 6e-06,
+        "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
+        "input_cost_per_token": 3e-05,
+        "input_cost_per_token_above_272k_tokens": 6e-05,
+        "input_cost_per_token_priority": 6e-05,
+        "input_cost_per_token_above_272k_tokens_priority": 0.00012,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 0.00018,
+        "output_cost_per_token_above_272k_tokens": 0.00027,
+        "output_cost_per_token_priority": 0.00036,
+        "output_cost_per_token_above_272k_tokens_priority": 0.00054,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-pro",
+        "supported_endpoints": [
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": false,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
+    "azure_ai/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_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_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "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_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
+    "azure_ai/gpt-5.4-mini-2026-03-17": {
+        "cache_read_input_token_cost": 7.5e-08,
+        "cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
+        "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_priority": 1.5e-06,
+        "input_cost_per_token_above_272k_tokens_priority": 3e-06,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "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_priority": 9e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 1.35e-05,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-mini",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
+    "azure_ai/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_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_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
+    "azure_ai/gpt-5.4-nano-2026-03-17": {
+        "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,
+        "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_priority": 4e-07,
+        "input_cost_per_token_above_272k_tokens_priority": 8e-07,
+        "litellm_provider": "azure_ai",
+        "max_input_tokens": 400000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token_above_272k_tokens": 1.875e-06,
+        "output_cost_per_token_priority": 2.5e-06,
+        "output_cost_per_token_above_272k_tokens_priority": 3.75e-06,
+        "source": "https://ai.azure.com/catalog/models/gpt-5.4-nano",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": false
+    },
     "azure_ai/model_router": {
         "input_cost_per_token": 1.4e-07,
         "output_cost_per_token": 0,