diff --git a/model_cost_data/model_prices_and_context_window.json b/model_cost_data/model_prices_and_context_window.json
index 55a50e04..5689201e 100644
--- a/model_cost_data/model_prices_and_context_window.json
+++ b/model_cost_data/model_prices_and_context_window.json
@@ -14,7 +14,8 @@
         "supports_audio_output": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD"
     },
     "omni-moderation-latest": {
         "max_tokens": 32768,
@@ -193,14 +194,44 @@
         "max_tokens": 65536,
         "max_input_tokens": 128000,
         "max_output_tokens": 65536,
-        "input_cost_per_token": 0.000003,
-        "output_cost_per_token": 0.000012,
-        "cache_read_input_token_cost": 0.0000015,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
         "litellm_provider": "openai",
         "mode": "chat",
         "supports_vision": true,
         "supports_prompt_caching": true
     },
+    "o3-mini": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
+    "o3-mini-2025-01-31": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": false,
+        "supports_vision": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
     "o1-mini-2024-09-12": {
         "max_tokens": 65536,
         "max_input_tokens": 128000,
@@ -441,7 +472,8 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "2025-06-06"
     },
     "gpt-4-32k": {
         "max_tokens": 4096,
@@ -540,7 +572,8 @@
         "mode": "chat",
         "supports_vision": true,
         "supports_prompt_caching": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "2024-12-06"
     },
     "gpt-4-1106-vision-preview": {
         "max_tokens": 4096,
@@ -552,7 +585,8 @@
         "mode": "chat",
         "supports_vision": true,
         "supports_prompt_caching": true,
-        "supports_system_messages": true
+        "supports_system_messages": true,
+        "deprecation_date": "2024-12-06"
     },
     "gpt-3.5-turbo": {
         "max_tokens": 4097,
@@ -887,7 +921,7 @@
     },
     "whisper-1": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0,
+        "input_cost_per_second": 0.0001,
         "output_cost_per_second": 0.0001, 
         "litellm_provider": "openai"
     }, 
@@ -901,6 +935,30 @@
         "input_cost_per_character": 0.000030,
         "litellm_provider": "openai"
     },
+    "azure/o3-mini": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_vision": false,
+        "supports_prompt_caching": true
+    },
+    "azure/o3-mini-2025-01-31": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "supports_vision": false,
+        "supports_prompt_caching": true
+    },
     "azure/tts-1": {
         "mode": "audio_speech", 
         "input_cost_per_character": 0.000015,
@@ -913,10 +971,34 @@
     },
     "azure/whisper-1": {
         "mode": "audio_transcription",
-        "input_cost_per_second": 0, 
+        "input_cost_per_second": 0.0001, 
         "output_cost_per_second": 0.0001, 
         "litellm_provider": "azure"
     },
+    "azure/deepseek-r1": {
+        "max_tokens": 8192,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.0,
+        "input_cost_per_token_cache_hit": 0.0,
+        "output_cost_per_token": 0.0,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_prompt_caching": true
+    },
+    "azure/o3-mini": {
+        "max_tokens": 100000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 100000,
+        "input_cost_per_token": 0.0000011,
+        "output_cost_per_token": 0.0000044,
+        "cache_read_input_token_cost": 0.00000055,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_vision": false,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true
+    },
     "azure/o1-mini": {
         "max_tokens": 65536,
         "max_input_tokens": 128000,
@@ -1007,6 +1089,7 @@
         "max_output_tokens": 16384,
         "input_cost_per_token": 0.00000275,
         "output_cost_per_token": 0.000011,
+        "cache_read_input_token_cost": 0.00000125,
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
@@ -1047,6 +1130,7 @@
         "max_output_tokens": 16384,
         "input_cost_per_token": 0.0000025,
         "output_cost_per_token": 0.000010,
+        "cache_read_input_token_cost": 0.00000125,
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
@@ -1223,7 +1307,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-03-31"
     },
     "azure/gpt-35-turbo-0613": {
         "max_tokens": 4097,
@@ -1234,7 +1319,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-02-13"
     },
     "azure/gpt-35-turbo-0301": {
         "max_tokens": 4097,
@@ -1245,7 +1331,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-02-13"
     },
     "azure/gpt-35-turbo-0125": {
         "max_tokens": 4096,
@@ -1256,7 +1343,8 @@
         "litellm_provider": "azure",
         "mode": "chat",
         "supports_function_calling": true,
-        "supports_parallel_function_calling": true
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-03-31"
     },
     "azure/gpt-35-turbo-16k": {
         "max_tokens": 4096,
@@ -2043,6 +2131,84 @@
         "supports_function_calling": true,
         "supports_vision": true
     },
+    "xai/grok-2-vision-1212": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 0.000002,
+        "input_cost_per_image": 0.000002,
+        "output_cost_per_token": 0.00001,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-2-vision-latest": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 0.000002,
+        "input_cost_per_image": 0.000002,
+        "output_cost_per_token": 0.00001,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-2-vision": {
+        "max_tokens": 32768,
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "input_cost_per_token": 0.000002,
+        "input_cost_per_image": 0.000002,
+        "output_cost_per_token": 0.00001,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-vision-beta": {
+        "max_tokens": 8192,
+        "max_input_tokens": 8192,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.000005,
+        "input_cost_per_image": 0.000005,
+        "output_cost_per_token": 0.000015,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_vision": true
+    },
+    "xai/grok-2-1212": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.00001,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
+    "xai/grok-2": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.00001,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
+    "xai/grok-2-latest": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.000002,
+        "output_cost_per_token": 0.00001,
+        "litellm_provider": "xai",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
     "deepseek/deepseek-coder": {
         "max_tokens": 4096,
         "max_input_tokens": 128000,
@@ -2057,6 +2223,19 @@
         "supports_tool_choice": true,
         "supports_prompt_caching": true
     },
+    "groq/deepseek-r1-distill-llama-70b": {
+        "max_tokens": 131072,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 131072,
+        "input_cost_per_token": 0.00000075,
+        "output_cost_per_token": 0.00000099,
+        "litellm_provider": "groq",
+        "mode": "chat",
+        "supports_system_messages": false,
+        "supports_function_calling": false, 
+        "supports_response_schema": false,
+        "supports_tool_choice": false
+    },
     "groq/llama-3.3-70b-versatile": {
         "max_tokens": 8192,
         "max_input_tokens": 128000,
@@ -2354,7 +2533,8 @@
         "tool_use_system_prompt_tokens": 264,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-03-01"
     },
     "claude-3-5-haiku-20241022": {
         "max_tokens": 8192,
@@ -2370,7 +2550,8 @@
         "tool_use_system_prompt_tokens": 264,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-10-01"
     },
     "claude-3-opus-20240229": {
         "max_tokens": 4096,
@@ -2387,7 +2568,8 @@
         "tool_use_system_prompt_tokens": 395,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-03-01"
     },
     "claude-3-sonnet-20240229": {
         "max_tokens": 4096,
@@ -2402,7 +2584,8 @@
         "tool_use_system_prompt_tokens": 159,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-07-21"
     },
     "claude-3-5-sonnet-20240620": {
         "max_tokens": 8192,
@@ -2419,7 +2602,8 @@
         "tool_use_system_prompt_tokens": 159,
         "supports_assistant_prefill": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-06-01"
     },
     "claude-3-5-sonnet-20241022": {
         "max_tokens": 8192,
@@ -2437,7 +2621,8 @@
         "supports_assistant_prefill": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "deprecation_date": "2025-10-01"
     },
     "text-bison": {
         "max_tokens": 2048,
@@ -2547,7 +2732,8 @@
         "output_cost_per_character": 0.0000005,
         "litellm_provider": "vertex_ai-chat-models",
         "mode": "chat",
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "chat-bison-32k": {
         "max_tokens": 8192,
@@ -2788,7 +2974,8 @@
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat",
         "supports_function_calling": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "gemini-1.0-ultra": {
         "max_tokens": 8192,
@@ -2833,7 +3020,8 @@
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat",
         "supports_function_calling": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "gemini-1.5-pro": { 
         "max_tokens": 8192,
@@ -2915,7 +3103,8 @@
         "supports_function_calling": true,
         "supports_tool_choice": true, 
         "supports_response_schema": true, 
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-05-24"
     },
     "gemini-1.5-pro-preview-0514": { 
         "max_tokens": 8192,
@@ -3120,7 +3309,8 @@
         "supports_function_calling": true,
         "supports_vision": true,
         "supports_response_schema": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-05-24"
     },
     "gemini-1.5-flash-preview-0514": {
         "max_tokens": 8192,
@@ -3188,8 +3378,9 @@
         "max_images_per_prompt": 16,
         "max_videos_per_prompt": 1,
         "max_video_length": 2,
-        "input_cost_per_token": 0.00000025, 
-        "output_cost_per_token": 0.0000005,
+        "input_cost_per_token": 0.0000005, 
+        "output_cost_per_token": 0.0000015,
+        "input_cost_per_image": 0.0025,
         "litellm_provider": "vertex_ai-vision-models",
         "mode": "chat",
         "supports_function_calling": true,
@@ -3203,8 +3394,9 @@
         "max_images_per_prompt": 16,
         "max_videos_per_prompt": 1,
         "max_video_length": 2,
-        "input_cost_per_token": 0.00000025, 
-        "output_cost_per_token": 0.0000005,
+        "input_cost_per_token": 0.0000005, 
+        "output_cost_per_token": 0.0000015,
+        "input_cost_per_image": 0.0025,
         "litellm_provider": "vertex_ai-vision-models",
         "mode": "chat",
         "supports_function_calling": true,
@@ -3218,13 +3410,15 @@
         "max_images_per_prompt": 16,
         "max_videos_per_prompt": 1,
         "max_video_length": 2,
-        "input_cost_per_token": 0.00000025, 
-        "output_cost_per_token": 0.0000005,
+        "input_cost_per_token": 0.0000005, 
+        "output_cost_per_token": 0.0000015,
+        "input_cost_per_image": 0.0025,
         "litellm_provider": "vertex_ai-vision-models",
         "mode": "chat",
         "supports_function_calling": true,
         "supports_vision": true,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
+        "deprecation_date": "2025-04-09"
     },
     "medlm-medium": {
         "max_tokens": 8192,
@@ -3312,6 +3506,39 @@
         "supports_audio_output": true,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash"
     },
+    "gemini-2.0-flash-thinking-exp-01-21": {
+        "max_tokens": 65536,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_images_per_prompt": 3000,
+        "max_videos_per_prompt": 10,
+        "max_video_length": 1,
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_pdf_size_mb": 30,
+        "input_cost_per_image": 0,
+        "input_cost_per_video_per_second": 0,
+        "input_cost_per_audio_per_second": 0,
+        "input_cost_per_token": 0,
+        "input_cost_per_character": 0, 
+        "input_cost_per_token_above_128k_tokens": 0, 
+        "input_cost_per_character_above_128k_tokens": 0, 
+        "input_cost_per_image_above_128k_tokens": 0,
+        "input_cost_per_video_per_second_above_128k_tokens": 0,
+        "input_cost_per_audio_per_second_above_128k_tokens": 0,
+        "output_cost_per_token": 0,
+        "output_cost_per_character": 0,
+        "output_cost_per_token_above_128k_tokens": 0,
+        "output_cost_per_character_above_128k_tokens": 0,
+        "litellm_provider": "vertex_ai-language-models",
+        "mode": "chat",
+        "supports_system_messages": true,
+        "supports_function_calling": false,
+        "supports_vision": true,
+        "supports_response_schema": false,
+        "supports_audio_output": false,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash"
+    },
     "gemini/gemini-2.0-flash-exp": {
         "max_tokens": 8192,
         "max_input_tokens": 1048576,
@@ -3691,6 +3918,16 @@
         "mode": "chat",
         "supports_function_calling": true
     },
+    "vertex_ai/codestral@2405": {
+        "max_tokens": 128000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "input_cost_per_token": 0.0000002,
+        "output_cost_per_token": 0.0000006,
+        "litellm_provider": "vertex_ai-mistral_models",
+        "mode": "chat",
+        "supports_function_calling": true
+    },
     "vertex_ai/imagegeneration@006": {
         "output_cost_per_image": 0.020,
         "litellm_provider": "vertex_ai-image-models",
@@ -3930,7 +4167,8 @@
         "supports_prompt_caching": true,
         "tpm": 4000000,
         "rpm": 2000,
-        "source": "https://ai.google.dev/pricing"
+        "source": "https://ai.google.dev/pricing",
+        "deprecation_date": "2025-05-24"
     },
     "gemini/gemini-1.5-flash": {
         "max_tokens": 8192,
@@ -4206,7 +4444,8 @@
         "supports_prompt_caching": true,
         "tpm": 4000000,
         "rpm": 1000,
-        "source": "https://ai.google.dev/pricing"
+        "source": "https://ai.google.dev/pricing",
+        "deprecation_date": "2025-05-24"
     },
     "gemini/gemini-1.5-pro-exp-0801": {
         "max_tokens": 8192,
@@ -7342,7 +7581,8 @@
         "input_cost_per_token": 0.000005, 
         "output_cost_per_token": 0.000005,
         "litellm_provider": "perplexity", 
-        "mode": "chat" 
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-large-128k-online": { 
         "max_tokens": 127072,
@@ -7351,7 +7591,8 @@
         "input_cost_per_token": 0.000001, 
         "output_cost_per_token": 0.000001,
         "litellm_provider": "perplexity", 
-        "mode": "chat" 
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-large-128k-chat": { 
         "max_tokens": 131072,
@@ -7360,7 +7601,8 @@
         "input_cost_per_token": 0.000001, 
         "output_cost_per_token": 0.000001,
         "litellm_provider": "perplexity", 
-        "mode": "chat" 
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-small-128k-chat": { 
         "max_tokens": 131072,
@@ -7369,7 +7611,8 @@
         "input_cost_per_token": 0.0000002, 
         "output_cost_per_token": 0.0000002,  
         "litellm_provider": "perplexity", 
-        "mode": "chat" 
+        "mode": "chat",
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-small-128k-online": { 
         "max_tokens": 127072,
@@ -7378,7 +7621,8 @@
         "input_cost_per_token": 0.0000002, 
         "output_cost_per_token": 0.0000002,  
         "litellm_provider": "perplexity", 
-        "mode": "chat" 
+        "mode": "chat" ,
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/pplx-7b-chat": { 
         "max_tokens": 8192,