phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

add azure o1 models to model cost map (#6075)

Browse source
This commit is contained in:
Ishaan Jaff 2024-10-05 13:22:06 +05:30 • committed by GitHub
parent c84cfe977e
commit 930606ad63
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 136 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

72
litellm/model_prices_and_context_window_backup.json
View file

@ -83,11 +83,13 @@
"max_output_tokens": 65536,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000012,
"cache_read_input_token_cost": 0.0000015,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"o1-preview": {
"max_tokens": 32768,
@ -109,11 +111,13 @@
"max_output_tokens": 32768,
"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": true
"supports_vision": true,
"supports_prompt_caching": true
},
"chatgpt-4o-latest": {
"max_tokens": 4096,
@ -582,17 +586,75 @@
"output_cost_per_second": 0.0001,
"litellm_provider": "azure"
},
"azure/o1-mini": {
"max_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 65536,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000012,
"cache_read_input_token_cost": 0.0000015,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/o1-mini-2024-09-12": {
"max_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 65536,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000012,
"cache_read_input_token_cost": 0.0000015,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/o1-preview": {
"max_tokens": 32768,
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000060,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/o1-preview-2024-09-12": {
"max_tokens": 32768,
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000060,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/gpt-4o": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.000015,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/gpt-4o-2024-08-06": {
"max_tokens": 16384,
@ -636,11 +698,13 @@
"max_output_tokens": 16384,
"input_cost_per_token": 0.000000165,
"output_cost_per_token": 0.00000066,
"cache_read_input_token_cost": 0.000000075,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/gpt-4-turbo-2024-04-09": {
"max_tokens": 4096,

72
model_prices_and_context_window.json
View file

@ -83,11 +83,13 @@
"max_output_tokens": 65536,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000012,
"cache_read_input_token_cost": 0.0000015,
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"o1-preview": {
"max_tokens": 32768,
@ -109,11 +111,13 @@
"max_output_tokens": 32768,
"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": true
"supports_vision": true,
"supports_prompt_caching": true
},
"chatgpt-4o-latest": {
"max_tokens": 4096,
@ -582,17 +586,75 @@
"output_cost_per_second": 0.0001,
"litellm_provider": "azure"
},
"azure/o1-mini": {
"max_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 65536,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000012,
"cache_read_input_token_cost": 0.0000015,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/o1-mini-2024-09-12": {
"max_tokens": 65536,
"max_input_tokens": 128000,
"max_output_tokens": 65536,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000012,
"cache_read_input_token_cost": 0.0000015,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/o1-preview": {
"max_tokens": 32768,
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000060,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/o1-preview-2024-09-12": {
"max_tokens": 32768,
"max_input_tokens": 128000,
"max_output_tokens": 32768,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000060,
"cache_read_input_token_cost": 0.0000075,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/gpt-4o": {
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000005,
"output_cost_per_token": 0.000015,
"cache_read_input_token_cost": 0.00000125,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/gpt-4o-2024-08-06": {
"max_tokens": 16384,
@ -636,11 +698,13 @@
"max_output_tokens": 16384,
"input_cost_per_token": 0.000000165,
"output_cost_per_token": 0.00000066,
"cache_read_input_token_cost": 0.000000075,
"litellm_provider": "azure",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_vision": true
"supports_vision": true,
"supports_prompt_caching": true
},
"azure/gpt-4-turbo-2024-04-09": {
"max_tokens": 4096,