From eb301a7f87a48952dfc4ea3f69b6812fe96a6082 Mon Sep 17 00:00:00 2001
From: Marty Sullivan <marty-sullivan@users.noreply.github.com>
Date: Tue, 18 Nov 2025 22:58:06 -0500
Subject: [PATCH] Add Azure models 2025 11 to cost maps (#16762)

* add gpt-realtime models for azure

* update backup models w/ azure realtime

* add azure gpt-5.1 models to cost map

* add gpt-audio azure models to cost map

* add gpt-4o-transcribe-diarize azure model cost
---
 ...odel_prices_and_context_window_backup.json | 275 ++++++++++++++++++
 model_prices_and_context_window.json          | 275 ++++++++++++++++++
 2 files changed, 550 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 351e01bc45e..e77e67bf70d 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -1987,6 +1987,68 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/gpt-audio-2025-08-28": {
+        "input_cost_per_audio_token": 4e-05,
+        "input_cost_per_token": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": false,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "azure/gpt-audio-mini-2025-10-06": {
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2.4e-06,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": false,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "azure/gpt-4o-audio-preview-2024-12-17": {
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
@@ -2100,6 +2162,70 @@
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
+    "azure/gpt-realtime-2025-08-28": {
+        "cache_creation_input_audio_token_cost": 4e-06,
+        "cache_read_input_token_cost": 4e-06,
+        "input_cost_per_audio_token": 3.2e-05,
+        "input_cost_per_image": 5e-06,
+        "input_cost_per_token": 4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_audio_token": 6.4e-05,
+        "output_cost_per_token": 1.6e-05,
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "azure/gpt-realtime-mini-2025-10-06": {
+        "cache_creation_input_audio_token_cost": 3e-07,
+        "cache_read_input_token_cost": 6e-08,
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_image": 8e-07,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2.4e-06,
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
     "azure/gpt-4o-mini-transcribe": {
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 1.25e-06,
@@ -2187,6 +2313,155 @@
             "/v1/audio/transcriptions"
         ]
     },
+    "azure/gpt-4o-transcribe-diarize": {
+        "input_cost_per_audio_token": 6e-06,
+        "input_cost_per_token": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 16000,
+        "max_output_tokens": 2000,
+        "mode": "audio_transcription",
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/audio/transcriptions"
+        ]
+    },
+   "azure/gpt-5.1-2025-11-13": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_priority": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+   "azure/gpt-5.1-chat-2025-11-13": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_priority": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": false,
+        "supports_vision": true
+    },
+   "azure/gpt-5.1-codex-2025-11-13": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_priority": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "supported_endpoints": [
+            "/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": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "azure/gpt-5.1-codex-mini-2025-11-13": {
+        "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost_priority": 4.5e-08,
+        "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_priority": 4.5e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2e-06,
+        "output_cost_per_token_priority": 3.6e-06,
+        "supported_endpoints": [
+            "/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": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/gpt-5": {
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 351e01bc45e..e77e67bf70d 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -1987,6 +1987,68 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "azure/gpt-audio-2025-08-28": {
+        "input_cost_per_audio_token": 4e-05,
+        "input_cost_per_token": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_audio_token": 8e-05,
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": false,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "azure/gpt-audio-mini-2025-10-06": {
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2.4e-06,
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supported_modalities": [
+            "text",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": false,
+        "supports_reasoning": false,
+        "supports_response_schema": false,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
     "azure/gpt-4o-audio-preview-2024-12-17": {
         "input_cost_per_audio_token": 4e-05,
         "input_cost_per_token": 2.5e-06,
@@ -2100,6 +2162,70 @@
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
+    "azure/gpt-realtime-2025-08-28": {
+        "cache_creation_input_audio_token_cost": 4e-06,
+        "cache_read_input_token_cost": 4e-06,
+        "input_cost_per_audio_token": 3.2e-05,
+        "input_cost_per_image": 5e-06,
+        "input_cost_per_token": 4e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_audio_token": 6.4e-05,
+        "output_cost_per_token": 1.6e-05,
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "azure/gpt-realtime-mini-2025-10-06": {
+        "cache_creation_input_audio_token_cost": 3e-07,
+        "cache_read_input_token_cost": 6e-08,
+        "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_image": 8e-07,
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 32000,
+        "max_output_tokens": 4096,
+        "max_tokens": 4096,
+        "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2.4e-06,
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "audio"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
     "azure/gpt-4o-mini-transcribe": {
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 1.25e-06,
@@ -2187,6 +2313,155 @@
             "/v1/audio/transcriptions"
         ]
     },
+    "azure/gpt-4o-transcribe-diarize": {
+        "input_cost_per_audio_token": 6e-06,
+        "input_cost_per_token": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 16000,
+        "max_output_tokens": 2000,
+        "mode": "audio_transcription",
+        "output_cost_per_token": 1e-05,
+        "supported_endpoints": [
+            "/v1/audio/transcriptions"
+        ]
+    },
+   "azure/gpt-5.1-2025-11-13": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_priority": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "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
+    },
+   "azure/gpt-5.1-chat-2025-11-13": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_priority": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 128000,
+        "max_output_tokens": 16384,
+        "max_tokens": 16384,
+        "mode": "chat",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": false,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": false,
+        "supports_vision": true
+    },
+   "azure/gpt-5.1-codex-2025-11-13": {
+        "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.5e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_priority": 2.5e-06,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_priority": 2e-05,
+        "supported_endpoints": [
+            "/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": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "azure/gpt-5.1-codex-mini-2025-11-13": {
+        "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost_priority": 4.5e-08,
+        "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_priority": 4.5e-07,
+        "litellm_provider": "azure",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "output_cost_per_token": 2e-06,
+        "output_cost_per_token_priority": 3.6e-06,
+        "supported_endpoints": [
+            "/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": false,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "azure/gpt-5": {
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_token": 1.25e-06,