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

Update several Azure AI models in model cost map (#6655)

Browse source 
* Adding Azure Phi 3/3.5 models to model cost map

* Update gpt-4o-mini models

* Adding missing Azure Mistral models to model cost map

* Adding Azure Llama3.2 models to model cost map

* Fix Gemini-1.5-flash pricing

* Fix Gemini-1.5-flash output pricing

* Fix Gemini-1.5-pro prices

* Fix Gemini-1.5-flash output prices

* Correct gemini-1.5-pro prices

* Correction on Vertex Llama3.2 entry

---------

Co-authored-by: Emerson Gomes <emerson.gomes@thalesgroup.com>
This commit is contained in:
Emerson Gomes 2024-11-07 23:11:14 -06:00 • committed by GitHub
parent eb47117800
commit d0d29d70de
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 188 additions and 36 deletions
Download patch file Download diff file Expand all files Collapse all files

224
model_prices_and_context_window.json
View file

@ -80,6 +80,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true
},
@ -94,6 +95,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true
},
@ -475,6 +477,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"ft:davinci-002": {
@ -762,6 +765,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true
},
"azure/gpt-4o-mini": {
@ -775,6 +779,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true
},
@ -789,6 +794,7 @@
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_prompt_caching": true
},
@ -1113,6 +1119,52 @@
"supports_function_calling": true,
"mode": "chat"
},
"azure_ai/mistral-large-2407": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000006,
"litellm_provider": "azure_ai",
"supports_function_calling": true,
"mode": "chat",
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview"
},
"azure_ai/ministral-3b": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000004,
"output_cost_per_token": 0.00000004,
"litellm_provider": "azure_ai",
"supports_function_calling": true,
"mode": "chat",
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview"
},
"azure_ai/Llama-3.2-11B-Vision-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 2048,
"input_cost_per_token": 0.00000037,
"output_cost_per_token": 0.00000037,
"litellm_provider": "azure_ai",
"supports_function_calling": true,
"supports_vision": true,
"mode": "chat",
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-11b-vision-instruct-offer?tab=Overview"
},
"azure_ai/Llama-3.2-90B-Vision-Instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 2048,
"input_cost_per_token": 0.00000204,
"output_cost_per_token": 0.00000204,
"litellm_provider": "azure_ai",
"supports_function_calling": true,
"supports_vision": true,
"mode": "chat",
"source": "https://azuremarketplace.microsoft.com/en/marketplace/apps/metagenai.meta-llama-3-2-90b-vision-instruct-offer?tab=Overview"
},
"azure_ai/Meta-Llama-3-70B-Instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@ -1152,6 +1204,105 @@
"mode": "chat",
"source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice"
},
"azure_ai/Phi-3.5-mini-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000052,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3.5-vision-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000052,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": true,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3.5-MoE-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000016,
"output_cost_per_token": 0.00000064,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3-mini-4k-instruct": {
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000052,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3-mini-128k-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.00000052,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3-small-8k-instruct": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.0000006,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3-small-128k-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000015,
"output_cost_per_token": 0.0000006,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3-medium-4k-instruct": {
"max_tokens": 4096,
"max_input_tokens": 4096,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000017,
"output_cost_per_token": 0.00000068,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/Phi-3-medium-128k-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000017,
"output_cost_per_token": 0.00000068,
"litellm_provider": "azure_ai",
"mode": "chat",
"supports_vision": false,
"source": "https://azure.microsoft.com/en-us/pricing/details/phi-3/"
},
"azure_ai/cohere-rerank-v3-multilingual": {
"max_tokens": 4096,
"max_input_tokens": 4096,
@ -2212,16 +2363,16 @@
"input_cost_per_image": 0.00032875,
"input_cost_per_audio_per_second": 0.00003125,
"input_cost_per_video_per_second": 0.00032875,
"input_cost_per_token": 0.000000078125,
"input_cost_per_character": 0.0000003125,
"input_cost_per_token": 0.00000125,
"input_cost_per_character": 0.0000003125,
"input_cost_per_image_above_128k_tokens": 0.0006575,
"input_cost_per_video_per_second_above_128k_tokens": 0.0006575,
"input_cost_per_audio_per_second_above_128k_tokens": 0.0000625,
"input_cost_per_token_above_128k_tokens": 0.00000015625,
"input_cost_per_character_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.0000025,
"input_cost_per_character_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.000005,
"output_cost_per_character": 0.00000125,
"output_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token_above_128k_tokens": 0.00001,
"output_cost_per_character_above_128k_tokens": 0.0000025,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
@ -2238,16 +2389,16 @@
"input_cost_per_image": 0.00032875,
"input_cost_per_audio_per_second": 0.00003125,
"input_cost_per_video_per_second": 0.00032875,
"input_cost_per_token": 0.000000078125,
"input_cost_per_character": 0.0000003125,
"input_cost_per_token": 0.00000125,
"input_cost_per_character": 0.0000003125,
"input_cost_per_image_above_128k_tokens": 0.0006575,
"input_cost_per_video_per_second_above_128k_tokens": 0.0006575,
"input_cost_per_audio_per_second_above_128k_tokens": 0.0000625,
"input_cost_per_token_above_128k_tokens": 0.00000015625,
"input_cost_per_character_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.0000025,
"input_cost_per_character_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.000005,
"output_cost_per_character": 0.00000125,
"output_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token_above_128k_tokens": 0.00001,
"output_cost_per_character_above_128k_tokens": 0.0000025,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
@ -2264,16 +2415,16 @@
"input_cost_per_image": 0.00032875,
"input_cost_per_audio_per_second": 0.00003125,
"input_cost_per_video_per_second": 0.00032875,
"input_cost_per_token": 0.000000078125,
"input_cost_per_character": 0.0000003125,
"input_cost_per_token": 0.00000125,
"input_cost_per_character": 0.0000003125,
"input_cost_per_image_above_128k_tokens": 0.0006575,
"input_cost_per_video_per_second_above_128k_tokens": 0.0006575,
"input_cost_per_audio_per_second_above_128k_tokens": 0.0000625,
"input_cost_per_token_above_128k_tokens": 0.00000015625,
"input_cost_per_character_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.0000003125,
"input_cost_per_token_above_128k_tokens": 0.0000025,
"input_cost_per_character_above_128k_tokens": 0.000000625,
"output_cost_per_token": 0.000005,
"output_cost_per_character": 0.00000125,
"output_cost_per_token_above_128k_tokens": 0.000000625,
"output_cost_per_token_above_128k_tokens": 0.00001,
"output_cost_per_character_above_128k_tokens": 0.0000025,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
@ -2373,17 +2524,17 @@
"input_cost_per_image": 0.00002,
"input_cost_per_video_per_second": 0.00002,
"input_cost_per_audio_per_second": 0.000002,
"input_cost_per_token": 0.000000004688,
"input_cost_per_token": 0.000000075,
"input_cost_per_character": 0.00000001875,
"input_cost_per_token_above_128k_tokens": 0.000001,
"input_cost_per_character_above_128k_tokens": 0.00000025,
"input_cost_per_image_above_128k_tokens": 0.00004,
"input_cost_per_video_per_second_above_128k_tokens": 0.00004,
"input_cost_per_audio_per_second_above_128k_tokens": 0.000004,
"output_cost_per_token": 0.0000000046875,
"output_cost_per_character": 0.00000001875,
"output_cost_per_token_above_128k_tokens": 0.000000009375,
"output_cost_per_character_above_128k_tokens": 0.0000000375,
"output_cost_per_token": 0.0000003,
"output_cost_per_character": 0.000000075,
"output_cost_per_token_above_128k_tokens": 0.0000006,
"output_cost_per_character_above_128k_tokens": 0.00000015,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_system_messages": true,
@ -2437,17 +2588,17 @@
"input_cost_per_image": 0.00002,
"input_cost_per_video_per_second": 0.00002,
"input_cost_per_audio_per_second": 0.000002,
"input_cost_per_token": 0.000000004688,
"input_cost_per_token": 0.000000075,
"input_cost_per_character": 0.00000001875,
"input_cost_per_token_above_128k_tokens": 0.000001,
"input_cost_per_character_above_128k_tokens": 0.00000025,
"input_cost_per_image_above_128k_tokens": 0.00004,
"input_cost_per_video_per_second_above_128k_tokens": 0.00004,
"input_cost_per_audio_per_second_above_128k_tokens": 0.000004,
"output_cost_per_token": 0.0000000046875,
"output_cost_per_character": 0.00000001875,
"output_cost_per_token_above_128k_tokens": 0.000000009375,
"output_cost_per_character_above_128k_tokens": 0.0000000375,
"output_cost_per_token": 0.0000003,
"output_cost_per_character": 0.000000075,
"output_cost_per_token_above_128k_tokens": 0.0000006,
"output_cost_per_character_above_128k_tokens": 0.00000015,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_system_messages": true,
@ -2469,17 +2620,17 @@
"input_cost_per_image": 0.00002,
"input_cost_per_video_per_second": 0.00002,
"input_cost_per_audio_per_second": 0.000002,
"input_cost_per_token": 0.000000004688,
"input_cost_per_token": 0.000000075,
"input_cost_per_character": 0.00000001875,
"input_cost_per_token_above_128k_tokens": 0.000001,
"input_cost_per_character_above_128k_tokens": 0.00000025,
"input_cost_per_image_above_128k_tokens": 0.00004,
"input_cost_per_video_per_second_above_128k_tokens": 0.00004,
"input_cost_per_audio_per_second_above_128k_tokens": 0.000004,
"output_cost_per_token": 0.0000000046875,
"output_cost_per_character": 0.00000001875,
"output_cost_per_token_above_128k_tokens": 0.000000009375,
"output_cost_per_character_above_128k_tokens": 0.0000000375,
"output_cost_per_token": 0.0000003,
"output_cost_per_character": 0.000000075,
"output_cost_per_token_above_128k_tokens": 0.0000006,
"output_cost_per_character_above_128k_tokens": 0.00000015,
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_system_messages": true,
@ -2501,7 +2652,7 @@
"input_cost_per_image": 0.00002,
"input_cost_per_video_per_second": 0.00002,
"input_cost_per_audio_per_second": 0.000002,
"input_cost_per_token": 0.000000004688,
"input_cost_per_token": 0.000000075,
"input_cost_per_character": 0.00000001875,
"input_cost_per_token_above_128k_tokens": 0.000001,
"input_cost_per_character_above_128k_tokens": 0.00000025,
@ -2714,14 +2865,15 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models"
},
"vertex_ai/meta/llama-3.2-90b-vision-instruct-maas": {
"max_tokens": 8192,
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_output_tokens": 2048,
"input_cost_per_token": 0.0,
"output_cost_per_token": 0.0,
"litellm_provider": "vertex_ai-llama_models",
"mode": "chat",
"supports_system_messages": true,
"supports_vision": true,
"source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas"
},
"vertex_ai/mistral-large@latest": {