Skip to content
This repository was archived by the owner on Jun 5, 2025. It is now read-only.

Update model_prices_and_context_window.json #1308

Merged
merged 1 commit into from
Mar 24, 2025
Merged

Update model_prices_and_context_window.json #1308

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
257 changes: 247 additions & 10 deletions model_cost_data/model_prices_and_context_window.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,12 @@
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.0000,
"search_context_size_medium": 0.0000,
"search_context_size_high": 0.0000
},
"deprecation_date": "date when the model becomes deprecated in the format YYYY-MM-DD"
},
"omni-moderation-latest": {
Expand Down Expand Up @@ -74,7 +80,63 @@
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.030,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.050
}
},
"gpt-4o-search-preview-2025-03-11": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.000010,
"input_cost_per_token_batches": 0.00000125,
"output_cost_per_token_batches": 0.00000500,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.030,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.050
}
},
"gpt-4o-search-preview": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.000010,
"input_cost_per_token_batches": 0.00000125,
"output_cost_per_token_batches": 0.00000500,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.030,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.050
}
},
"gpt-4.5-preview": {
"max_tokens": 16384,
Expand Down Expand Up @@ -199,7 +261,63 @@
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275,
"search_context_size_high": 0.030
}
},
"gpt-4o-mini-search-preview-2025-03-11":{
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.00000060,
"input_cost_per_token_batches": 0.000000075,
"output_cost_per_token_batches": 0.00000030,
"cache_read_input_token_cost": 0.000000075,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275,
"search_context_size_high": 0.030
}
},
"gpt-4o-mini-search-preview": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.00000060,
"input_cost_per_token_batches": 0.000000075,
"output_cost_per_token_batches": 0.00000030,
"cache_read_input_token_cost": 0.000000075,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.025,
"search_context_size_medium": 0.0275,
"search_context_size_high": 0.030
}
},
"gpt-4o-mini-2024-07-18": {
"max_tokens": 16384,
Expand All @@ -218,7 +336,54 @@
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"search_context_cost_per_query": {
"search_context_size_low": 30.00,
"search_context_size_medium": 35.00,
"search_context_size_high": 50.00
}
},
"o1-pro": {
"max_tokens": 100000,
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"input_cost_per_token": 0.00015,
"output_cost_per_token": 0.0006,
"input_cost_per_token_batches": 0.000075,
"output_cost_per_token_batches": 0.0003,
"litellm_provider": "openai",
"mode": "responses",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_native_streaming": false,
"supported_modalities": ["text", "image"],
"supported_endpoints": ["/v1/responses", "/v1/batch"]
},
"o1-pro-2025-03-19": {
"max_tokens": 100000,
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"input_cost_per_token": 0.00015,
"output_cost_per_token": 0.0006,
"input_cost_per_token_batches": 0.000075,
"output_cost_per_token_batches": 0.0003,
"litellm_provider": "openai",
"mode": "responses",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_native_streaming": false,
"supported_modalities": ["text", "image"],
"supported_endpoints": ["/v1/responses", "/v1/batch"]
},
"o1": {
"max_tokens": 100000,
Expand Down Expand Up @@ -383,7 +548,13 @@
"supports_vision": true,
"supports_prompt_caching": true,
"supports_system_messages": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.030,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.050
}
},
"gpt-4o-2024-11-20": {
"max_tokens": 16384,
Expand Down Expand Up @@ -1384,17 +1555,53 @@
"supports_vision": false,
"supports_prompt_caching": true
},
"azure/gpt-4.5-preview": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.000075,
"output_cost_per_token": 0.00015,
"input_cost_per_token_batches": 0.0000375,
"output_cost_per_token_batches": 0.000075,
"cache_read_input_token_cost": 0.0000375,
"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_system_messages": true,
"supports_tool_choice": true
},
"azure/gpt-4o": {
"max_tokens": 4096,
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.000015,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"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/gpt-4o-2024-11-20": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"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
Expand All @@ -1403,8 +1610,24 @@
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000275,
"output_cost_per_token": 0.000011,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"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/gpt-4o-2024-08-06": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000025,
"output_cost_per_token": 0.00001,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
Expand All @@ -1421,12 +1644,14 @@
"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,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true,
"supports_tool_choice": true
},
"azure/us/gpt-4o-2024-11-20": {
Expand Down Expand Up @@ -2014,6 +2239,18 @@
"mode": "chat",
"supports_tool_choice": true
},
"azure_ai/mistral-small-2503": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.000001,
"output_cost_per_token": 0.000003,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"supports_tool_choice": true
},
"azure_ai/mistral-large-2407": {
"max_tokens": 4096,
"max_input_tokens": 128000,
Expand Down