scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 86

Litellm dev 12 17 2024 p3 (#7279)

Browse source 
* build(model_prices_and_context_window.json): add new o1 model

* build(model_prices_and_context_window.json): add new gpt-4o-realtime preview models

* build(model_prices_and_context_window.json): add dec 17th gpt-4o realtime preview models

* build(model_prices_and_context_window.json): update gpt-4o model audio token pricing + add audio token cached cost

* build(model_prices_and_context_window.json): add new 'gpt-4o-mini-audio-preview-2024-12-17' model pricing

* build(model_prices_and_context_window.json): add 'supports_prompt_caching' for openai finetune models + cache read cost

* build(model_prices_and_context_window.json): add new o1 models
This commit is contained in:
Krish Dholakia 2024-12-17 15:06:29 -08:00 • committed by GitHub
parent 019ddc32d6
commit f42b31b743
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 264 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

134
litellm/model_prices_and_context_window_backup.json
View file

@ -71,6 +71,21 @@
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini-audio-preview-2024-12-17": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000015,
"input_cost_per_audio_token": 0.00001,
"output_cost_per_token": 0.0000006,
"output_cost_per_audio_token": 0.00002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini": {
"max_tokens": 16384,
"max_input_tokens": 128000,
@ -101,6 +116,20 @@
"supports_vision": true,
"supports_prompt_caching": true
},
"o1": {
"max_tokens": 100000,
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.00006,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false,
"supports_prompt_caching": true
},
"o1-mini": {
"max_tokens": 65536,
"max_input_tokens": 128000,
@ -157,6 +186,20 @@
"supports_vision": false,
"supports_prompt_caching": true
},
"o1-2024-12-17": {
"max_tokens": 100000,
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000060,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false,
"supports_prompt_caching": true
},
"chatgpt-4o-latest": {
"max_tokens": 4096,
"max_input_tokens": 128000,
@ -213,6 +256,89 @@
"supports_vision": true,
"supports_prompt_caching": true
},
"gpt-4o-realtime-preview-2024-10-01": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"input_cost_per_audio_token": 0.0001,
"cache_read_input_token_cost": 0.0000025,
"cache_creation_input_audio_token_cost": 0.00002,
"output_cost_per_token": 0.00002,
"output_cost_per_audio_token": 0.0002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-realtime-preview": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"input_cost_per_audio_token": 0.00004,
"cache_read_input_token_cost": 0.0000025,
"output_cost_per_token": 0.00002,
"output_cost_per_audio_token": 0.00008,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-realtime-preview-2024-12-17": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"input_cost_per_audio_token": 0.00004,
"cache_read_input_token_cost": 0.0000025,
"output_cost_per_token": 0.00002,
"output_cost_per_audio_token": 0.00008,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini-realtime-preview": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.0000006,
"input_cost_per_audio_token": 0.00001,
"cache_read_input_token_cost": 0.0000003,
"cache_creation_input_audio_token_cost": 0.0000003,
"output_cost_per_token": 0.0000024,
"output_cost_per_audio_token": 0.00002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini-realtime-preview-2024-12-17": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.0000006,
"input_cost_per_audio_token": 0.00001,
"cache_read_input_token_cost": 0.0000003,
"cache_creation_input_audio_token_cost": 0.0000003,
"output_cost_per_token": 0.0000024,
"output_cost_per_audio_token": 0.00002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4-turbo-preview": {
"max_tokens": 4096,
"max_input_tokens": 128000,
@ -489,26 +615,30 @@
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000375,
"cache_creation_input_token_cost": 0.000001875,
"output_cost_per_token": 0.000015,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"ft:gpt-4o-mini-2024-07-18": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000003,
"cache_read_input_token_cost": 0.00000015,
"output_cost_per_token": 0.0000012,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"ft:davinci-002": {
"max_tokens": 16384,

134
model_prices_and_context_window.json
View file

@ -71,6 +71,21 @@
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini-audio-preview-2024-12-17": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000015,
"input_cost_per_audio_token": 0.00001,
"output_cost_per_token": 0.0000006,
"output_cost_per_audio_token": 0.00002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini": {
"max_tokens": 16384,
"max_input_tokens": 128000,
@ -101,6 +116,20 @@
"supports_vision": true,
"supports_prompt_caching": true
},
"o1": {
"max_tokens": 100000,
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.00006,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false,
"supports_prompt_caching": true
},
"o1-mini": {
"max_tokens": 65536,
"max_input_tokens": 128000,
@ -157,6 +186,20 @@
"supports_vision": false,
"supports_prompt_caching": true
},
"o1-2024-12-17": {
"max_tokens": 100000,
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000060,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": false,
"supports_prompt_caching": true
},
"chatgpt-4o-latest": {
"max_tokens": 4096,
"max_input_tokens": 128000,
@ -213,6 +256,89 @@
"supports_vision": true,
"supports_prompt_caching": true
},
"gpt-4o-realtime-preview-2024-10-01": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"input_cost_per_audio_token": 0.0001,
"cache_read_input_token_cost": 0.0000025,
"cache_creation_input_audio_token_cost": 0.00002,
"output_cost_per_token": 0.00002,
"output_cost_per_audio_token": 0.0002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-realtime-preview": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"input_cost_per_audio_token": 0.00004,
"cache_read_input_token_cost": 0.0000025,
"output_cost_per_token": 0.00002,
"output_cost_per_audio_token": 0.00008,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-realtime-preview-2024-12-17": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"input_cost_per_audio_token": 0.00004,
"cache_read_input_token_cost": 0.0000025,
"output_cost_per_token": 0.00002,
"output_cost_per_audio_token": 0.00008,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini-realtime-preview": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.0000006,
"input_cost_per_audio_token": 0.00001,
"cache_read_input_token_cost": 0.0000003,
"cache_creation_input_audio_token_cost": 0.0000003,
"output_cost_per_token": 0.0000024,
"output_cost_per_audio_token": 0.00002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4o-mini-realtime-preview-2024-12-17": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.0000006,
"input_cost_per_audio_token": 0.00001,
"cache_read_input_token_cost": 0.0000003,
"cache_creation_input_audio_token_cost": 0.0000003,
"output_cost_per_token": 0.0000024,
"output_cost_per_audio_token": 0.00002,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_audio_input": true,
"supports_audio_output": true
},
"gpt-4-turbo-preview": {
"max_tokens": 4096,
"max_input_tokens": 128000,
@ -489,26 +615,30 @@
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.00000375,
"cache_creation_input_token_cost": 0.000001875,
"output_cost_per_token": 0.000015,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"ft:gpt-4o-mini-2024-07-18": {
"max_tokens": 16384,
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"input_cost_per_token": 0.0000003,
"cache_read_input_token_cost": 0.00000015,
"output_cost_per_token": 0.0000012,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"ft:davinci-002": {
"max_tokens": 16384,