phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-25 02:34:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add gpt 4.1 models

Browse source
This commit is contained in:
Ishaan Jaff 2025-04-14 11:47:27 -07:00
parent 64bb89c70f
commit 72d24965c0
2 changed files with 144 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

72
litellm/model_prices_and_context_window_backup.json
View file

@ -89,6 +89,78 @@
"search_context_size_high": 0.050
}
},
"gpt-4.1": {
"max_input_tokens": 1014808,
"max_output_tokens": 32768,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000008,
"input_cost_per_token_batches": 0.000001,
"output_cost_per_token_batches": 0.000004,
"cache_read_input_token_cost": 0.0000005,
"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-4.1-mini": {
"max_input_tokens": 1014808,
"max_output_tokens": 32768,
"input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000016,
"input_cost_per_token_batches": 0.0000002,
"output_cost_per_token_batches": 0.0000008,
"cache_read_input_token_cost": 0.0000001,
"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-4.1-nano": {
"max_input_tokens": 1014808,
"max_output_tokens": 32768,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000004,
"input_cost_per_token_batches": 0.00000005,
"output_cost_per_token_batches": 0.00000020,
"cache_read_input_token_cost": 0.000000025,
"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
}
},
"watsonx/ibm/granite-3-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,

72
model_prices_and_context_window.json
View file

@ -89,6 +89,78 @@
"search_context_size_high": 0.050
}
},
"gpt-4.1": {
"max_input_tokens": 1014808,
"max_output_tokens": 32768,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000008,
"input_cost_per_token_batches": 0.000001,
"output_cost_per_token_batches": 0.000004,
"cache_read_input_token_cost": 0.0000005,
"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-4.1-mini": {
"max_input_tokens": 1014808,
"max_output_tokens": 32768,
"input_cost_per_token": 0.0000004,
"output_cost_per_token": 0.0000016,
"input_cost_per_token_batches": 0.0000002,
"output_cost_per_token_batches": 0.0000008,
"cache_read_input_token_cost": 0.0000001,
"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-4.1-nano": {
"max_input_tokens": 1014808,
"max_output_tokens": 32768,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.0000004,
"input_cost_per_token_batches": 0.00000005,
"output_cost_per_token_batches": 0.00000020,
"cache_read_input_token_cost": 0.000000025,
"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
}
},
"watsonx/ibm/granite-3-8b-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,