stacklok · aponcedeleonch · Feb 17, 2025 · Feb 16, 2025
diff --git a/model_cost_data/model_prices_and_context_window.json b/model_cost_data/model_prices_and_context_window.json
@@ -1412,6 +1412,19 @@
         "deprecation_date": "2025-03-31",
         "supports_tool_choice": true
     },
+    "azure/gpt-3.5-turbo-0125": {
+        "max_tokens": 4096,
+        "max_input_tokens": 16384,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000005,
+        "output_cost_per_token": 0.0000015,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "deprecation_date": "2025-03-31",
+        "supports_tool_choice": true
+    },
     "azure/gpt-35-turbo-16k": {
         "max_tokens": 4096,
         "max_input_tokens": 16385,
@@ -1433,6 +1446,17 @@
         "supports_function_calling": true,
         "supports_tool_choice": true
     },
+    "azure/gpt-3.5-turbo": {
+        "max_tokens": 4096,
+        "max_input_tokens": 4097,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.0000005,
+        "output_cost_per_token": 0.0000015,
+        "litellm_provider": "azure",
+        "mode": "chat",
+        "supports_function_calling": true,
+        "supports_tool_choice": true
+    },
     "azure/gpt-3.5-turbo-instruct-0914": {
         "max_tokens": 4097,
         "max_input_tokens": 4097,
@@ -3634,6 +3658,42 @@
         "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models",
         "supports_tool_choice": true
     },
+    "gemini-2.0-pro-exp-02-05": {
+        "max_tokens": 8192,
+        "max_input_tokens": 2097152,
+        "max_output_tokens": 8192,
+        "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": true,
+        "supports_vision": true,
+        "supports_audio_input": true,
+        "supports_video_input": true,
+        "supports_pdf_input": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
+    },
     "gemini-2.0-flash-exp": {
         "max_tokens": 8192,
         "max_input_tokens": 1048576,
@@ -7035,7 +7095,9 @@
         "input_cost_per_token": 0.00000072,
         "output_cost_per_token": 0.00000072,
         "litellm_provider": "bedrock_converse",
-        "mode": "chat"
+        "mode": "chat",
+        "supports_function_calling": true, 
+        "supports_tool_choice": false
     },
     "meta.llama2-13b-chat-v1": {
         "max_tokens": 4096, 
@@ -7375,6 +7437,17 @@
         "supports_function_calling": true, 
         "supports_tool_choice": false
     },
+    "us.meta.llama3-3-70b-instruct-v1:0": {
+        "max_tokens": 4096, 
+        "max_input_tokens": 128000,
+        "max_output_tokens": 4096,
+        "input_cost_per_token": 0.00000072,
+        "output_cost_per_token": 0.00000072,
+        "litellm_provider": "bedrock_converse",
+        "mode": "chat",
+        "supports_function_calling": true, 
+        "supports_tool_choice": false
+    },
     "512-x-512/50-steps/stability.stable-diffusion-xl-v0": {
         "max_tokens": 77, 
         "max_input_tokens": 77, 
@@ -8084,8 +8157,7 @@
         "input_cost_per_token": 0.00000035, 
         "output_cost_per_token": 0.00000140,  
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/codellama-70b-instruct": { 
         "max_tokens": 16384,
@@ -8094,8 +8166,7 @@
         "input_cost_per_token": 0.00000070, 
         "output_cost_per_token": 0.00000280,  
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/llama-3.1-70b-instruct": { 
         "max_tokens": 131072,
@@ -8104,8 +8175,7 @@
         "input_cost_per_token": 0.000001, 
         "output_cost_per_token": 0.000001,
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/llama-3.1-8b-instruct": { 
         "max_tokens": 131072,
@@ -8114,8 +8184,7 @@
         "input_cost_per_token": 0.0000002, 
         "output_cost_per_token": 0.0000002,  
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/llama-3.1-sonar-huge-128k-online": { 
         "max_tokens": 127072,
@@ -8125,8 +8194,7 @@
         "output_cost_per_token": 0.000005,
         "litellm_provider": "perplexity", 
         "mode": "chat",
-        "deprecation_date": "2025-02-22",
-        "supports_tool_choice": true
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-large-128k-online": { 
         "max_tokens": 127072,
@@ -8136,8 +8204,7 @@
         "output_cost_per_token": 0.000001,
         "litellm_provider": "perplexity", 
         "mode": "chat",
-        "deprecation_date": "2025-02-22",
-        "supports_tool_choice": true
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-large-128k-chat": { 
         "max_tokens": 131072,
@@ -8147,8 +8214,7 @@
         "output_cost_per_token": 0.000001,
         "litellm_provider": "perplexity", 
         "mode": "chat",
-        "deprecation_date": "2025-02-22",
-        "supports_tool_choice": true
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-small-128k-chat": { 
         "max_tokens": 131072,
@@ -8158,8 +8224,7 @@
         "output_cost_per_token": 0.0000002,  
         "litellm_provider": "perplexity", 
         "mode": "chat",
-        "deprecation_date": "2025-02-22",
-        "supports_tool_choice": true
+        "deprecation_date": "2025-02-22"
     },
     "perplexity/llama-3.1-sonar-small-128k-online": { 
         "max_tokens": 127072,
@@ -8169,8 +8234,43 @@
         "output_cost_per_token": 0.0000002,  
         "litellm_provider": "perplexity", 
         "mode": "chat" ,
-        "deprecation_date": "2025-02-22",
-        "supports_tool_choice": true
+        "deprecation_date": "2025-02-22"
+    },
+    "perplexity/sonar": { 
+        "max_tokens": 127072,
+        "max_input_tokens": 127072,
+        "max_output_tokens": 127072,
+        "input_cost_per_token": 0.000001, 
+        "output_cost_per_token": 0.000001,  
+        "litellm_provider": "perplexity", 
+        "mode": "chat" 
+    },
+    "perplexity/sonar-pro": { 
+        "max_tokens": 200000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8096,
+        "input_cost_per_token": 0.000003, 
+        "output_cost_per_token": 0.000015,  
+        "litellm_provider": "perplexity", 
+        "mode": "chat" 
+    },
+    "perplexity/sonar": { 
+        "max_tokens": 127072,
+        "max_input_tokens": 127072,
+        "max_output_tokens": 127072,
+        "input_cost_per_token": 0.000001, 
+        "output_cost_per_token": 0.000001,  
+        "litellm_provider": "perplexity", 
+        "mode": "chat" 
+    },
+    "perplexity/sonar-pro": { 
+        "max_tokens": 200000,
+        "max_input_tokens": 200000,
+        "max_output_tokens": 8096,
+        "input_cost_per_token": 0.000003, 
+        "output_cost_per_token": 0.000015,  
+        "litellm_provider": "perplexity", 
+        "mode": "chat" 
     },
     "perplexity/pplx-7b-chat": { 
         "max_tokens": 8192,
@@ -8179,8 +8279,7 @@
         "input_cost_per_token": 0.00000007, 
         "output_cost_per_token": 0.00000028, 
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/pplx-70b-chat": {  
         "max_tokens": 4096,
@@ -8189,8 +8288,7 @@
         "input_cost_per_token": 0.00000070, 
         "output_cost_per_token": 0.00000280, 
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/pplx-7b-online": { 
         "max_tokens": 4096,
@@ -8200,8 +8298,7 @@
         "output_cost_per_token": 0.00000028, 
         "input_cost_per_request": 0.005,
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/pplx-70b-online": { 
         "max_tokens": 4096,
@@ -8211,8 +8308,7 @@
         "output_cost_per_token": 0.00000280, 
         "input_cost_per_request": 0.005,
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/llama-2-70b-chat": { 
         "max_tokens": 4096,
@@ -8221,8 +8317,7 @@
         "input_cost_per_token": 0.00000070, 
         "output_cost_per_token": 0.00000280,
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/mistral-7b-instruct": { 
         "max_tokens": 4096,
@@ -8231,8 +8326,7 @@
         "input_cost_per_token": 0.00000007,
         "output_cost_per_token": 0.00000028,
         "litellm_provider": "perplexity", 
-        "mode": "chat" ,
-        "supports_tool_choice": true
+        "mode": "chat" 
     },
     "perplexity/mixtral-8x7b-instruct": {
         "max_tokens": 4096,
@@ -8241,8 +8335,7 @@
         "input_cost_per_token": 0.00000007,
         "output_cost_per_token": 0.00000028,
         "litellm_provider": "perplexity",
-        "mode": "chat",
-        "supports_tool_choice": true
+        "mode": "chat"
     },
     "perplexity/sonar-small-chat": {
         "max_tokens": 16384,
@@ -8251,8 +8344,7 @@
         "input_cost_per_token": 0.00000007,
         "output_cost_per_token": 0.00000028,
         "litellm_provider": "perplexity",
-        "mode": "chat",
-        "supports_tool_choice": true
+        "mode": "chat"
     },
     "perplexity/sonar-small-online": {
         "max_tokens": 12000,
@@ -8262,8 +8354,7 @@
         "output_cost_per_token": 0.00000028,
         "input_cost_per_request": 0.005,
         "litellm_provider": "perplexity",
-        "mode": "chat",
-        "supports_tool_choice": true
+        "mode": "chat"
     },
     "perplexity/sonar-medium-chat": {
         "max_tokens": 16384,
@@ -8272,8 +8363,7 @@
         "input_cost_per_token": 0.0000006,
         "output_cost_per_token": 0.0000018,
         "litellm_provider": "perplexity",
-        "mode": "chat",
-        "supports_tool_choice": true
+        "mode": "chat"
     },
     "perplexity/sonar-medium-online": {
         "max_tokens": 12000,
@@ -8283,8 +8373,7 @@
         "output_cost_per_token": 0.0000018,
         "input_cost_per_request": 0.005,
         "litellm_provider": "perplexity",
-        "mode": "chat",
-        "supports_tool_choice": true
+        "mode": "chat"
     },
     "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": {
         "max_tokens": 16384,
@@ -9044,4 +9133,4 @@
         "output_cost_per_second": 0.00, 
         "litellm_provider": "assemblyai"
     }
-}
+}