diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index bbcad25f8a7..70f8623597d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1083,11 +1083,11 @@ "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token": 0.000005, - "input_cost_per_audio_token": 0.00004, + "input_cost_per_audio_token": 0.0001, "cache_read_input_token_cost": 0.0000025, - "cache_creation_input_audio_token_cost": 0.0000025, + "cache_creation_input_audio_token_cost": 0.00002, "output_cost_per_token": 0.00002, - "output_cost_per_audio_token": 0.00008, + "output_cost_per_audio_token": 0.0002, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -1102,11 +1102,11 @@ "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token": 0.0000055, - "input_cost_per_audio_token": 0.000044, + "input_cost_per_audio_token": 0.00011, "cache_read_input_token_cost": 0.00000275, - "cache_creation_input_audio_token_cost": 0.00000275, + "cache_creation_input_audio_token_cost": 0.000022, "output_cost_per_token": 0.000022, - "output_cost_per_audio_token": 0.000088, + "output_cost_per_audio_token": 0.00022, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -1121,11 +1121,11 @@ "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token": 0.0000055, - "input_cost_per_audio_token": 0.000044, + "input_cost_per_audio_token": 0.00011, "cache_read_input_token_cost": 0.00000275, - "cache_creation_input_audio_token_cost": 0.00000275, + "cache_creation_input_audio_token_cost": 0.000022, "output_cost_per_token": 0.000022, - "output_cost_per_audio_token": 0.000088, + "output_cost_per_audio_token": 0.00022, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -1429,6 +1429,36 @@ "supports_vision": true, "supports_tool_choice": true }, + "azure/us/gpt-4o-2024-11-20": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "cache_creation_input_token_cost": 0.00000138, + "output_cost_per_token": 0.000011, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-4o-2024-11-20": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "cache_creation_input_token_cost": 0.00000138, + "output_cost_per_token": 0.000011, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_tool_choice": true + }, "azure/gpt-4o-2024-05-13": { "max_tokens": 4096, "max_input_tokens": 128000, @@ -1459,6 +1489,38 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "azure/us/gpt-4o-2024-08-06": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "output_cost_per_token": 0.000011, + "cache_read_input_token_cost": 0.000001375, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-4o-2024-08-06": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "output_cost_per_token": 0.000011, + "cache_read_input_token_cost": 0.000001375, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, "azure/global-standard/gpt-4o-2024-11-20": { "max_tokens": 16384, "max_input_tokens": 128000, @@ -1519,6 +1581,38 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "azure/us/gpt-4o-mini-2024-07-18": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000000165, + "output_cost_per_token": 0.00000066, + "cache_read_input_token_cost": 0.000000083, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-4o-mini-2024-07-18": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000000165, + "output_cost_per_token": 0.00000066, + "cache_read_input_token_cost": 0.000000083, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, "azure/gpt-4-turbo-2024-04-09": { "max_tokens": 4096, "max_input_tokens": 128000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index bbcad25f8a7..70f8623597d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1083,11 +1083,11 @@ "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token": 0.000005, - "input_cost_per_audio_token": 0.00004, + "input_cost_per_audio_token": 0.0001, "cache_read_input_token_cost": 0.0000025, - "cache_creation_input_audio_token_cost": 0.0000025, + "cache_creation_input_audio_token_cost": 0.00002, "output_cost_per_token": 0.00002, - "output_cost_per_audio_token": 0.00008, + "output_cost_per_audio_token": 0.0002, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -1102,11 +1102,11 @@ "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token": 0.0000055, - "input_cost_per_audio_token": 0.000044, + "input_cost_per_audio_token": 0.00011, "cache_read_input_token_cost": 0.00000275, - "cache_creation_input_audio_token_cost": 0.00000275, + "cache_creation_input_audio_token_cost": 0.000022, "output_cost_per_token": 0.000022, - "output_cost_per_audio_token": 0.000088, + "output_cost_per_audio_token": 0.00022, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -1121,11 +1121,11 @@ "max_input_tokens": 128000, "max_output_tokens": 4096, "input_cost_per_token": 0.0000055, - "input_cost_per_audio_token": 0.000044, + "input_cost_per_audio_token": 0.00011, "cache_read_input_token_cost": 0.00000275, - "cache_creation_input_audio_token_cost": 0.00000275, + "cache_creation_input_audio_token_cost": 0.000022, "output_cost_per_token": 0.000022, - "output_cost_per_audio_token": 0.000088, + "output_cost_per_audio_token": 0.00022, "litellm_provider": "azure", "mode": "chat", "supports_function_calling": true, @@ -1429,6 +1429,36 @@ "supports_vision": true, "supports_tool_choice": true }, + "azure/us/gpt-4o-2024-11-20": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "cache_creation_input_token_cost": 0.00000138, + "output_cost_per_token": 0.000011, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-4o-2024-11-20": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "cache_creation_input_token_cost": 0.00000138, + "output_cost_per_token": 0.000011, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_tool_choice": true + }, "azure/gpt-4o-2024-05-13": { "max_tokens": 4096, "max_input_tokens": 128000, @@ -1459,6 +1489,38 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "azure/us/gpt-4o-2024-08-06": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "output_cost_per_token": 0.000011, + "cache_read_input_token_cost": 0.000001375, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-4o-2024-08-06": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000275, + "output_cost_per_token": 0.000011, + "cache_read_input_token_cost": 0.000001375, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, "azure/global-standard/gpt-4o-2024-11-20": { "max_tokens": 16384, "max_input_tokens": 128000, @@ -1519,6 +1581,38 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "azure/us/gpt-4o-mini-2024-07-18": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000000165, + "output_cost_per_token": 0.00000066, + "cache_read_input_token_cost": 0.000000083, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, + "azure/eu/gpt-4o-mini-2024-07-18": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000000165, + "output_cost_per_token": 0.00000066, + "cache_read_input_token_cost": 0.000000083, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_tool_choice": true + }, "azure/gpt-4-turbo-2024-04-09": { "max_tokens": 4096, "max_input_tokens": 128000,