Skip to content

build(model_prices_and_context_window.json): add gpt-4.1 pricing #9990

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Apr 14, 2025
Merged

build(model_prices_and_context_window.json): add gpt-4.1 pricing #9990

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b2d38a1
build(model_prices_and_context_window.json): add gpt-4.1 pricing
krrishdholakia Apr 14, 2025
4daa76a
build(model_prices_and_context_window.json): add gpt-4.1-mini and gpt…
krrishdholakia Apr 14, 2025
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
138 changes: 138 additions & 0 deletions litellm/model_prices_and_context_window_backup.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,144 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-4.1": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-mini": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-mini-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-nano": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-nano-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4o": {
"max_tokens": 16384,
"max_input_tokens": 128000,
Expand Down
138 changes: 138 additions & 0 deletions model_prices_and_context_window.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,6 +64,144 @@
"supports_system_messages": true,
"supports_tool_choice": true
},
"gpt-4.1": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 2e-6,
"output_cost_per_token": 8e-6,
"input_cost_per_token_batches": 1e-6,
"output_cost_per_token_batches": 4e-6,
"cache_read_input_token_cost": 1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-mini": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-mini-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.4e-6,
"output_cost_per_token": 1.6e-6,
"input_cost_per_token_batches": 0.2e-6,
"output_cost_per_token_batches": 0.8e-6,
"cache_read_input_token_cost": 0.1e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-nano": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4.1-nano-2025-04-14": {
"max_tokens": 32768,
"max_input_tokens": 1047576,
"max_output_tokens": 32768,
"input_cost_per_token": 0.1e-6,
"output_cost_per_token": 0.4e-6,
"input_cost_per_token_batches": 0.05e-6,
"output_cost_per_token_batches": 0.2e-6,
"cache_read_input_token_cost": 0.025e-6,
"litellm_provider": "openai",
"mode": "chat",
"supported_endpoints": ["/v1/chat/completions", "/v1/batch", "/v1/responses"],
"supported_modalities": ["text", "image"],
"supported_output_modalities": ["text"],
"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_native_streaming": true
},
"gpt-4o": {
"max_tokens": 16384,
"max_input_tokens": 128000,
Expand Down
Loading