alihan/tokencost
1
0
Fork 0
mirror of https://github.com/AgentOps-AI/tokencost.git synced 2024-06-22 04:30:40 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update model_prices.json

Browse Source
This commit is contained in:
Alex Reibman
2024-04-22 23:50:00 -07:00
committed by GitHub
parent f6c853b802
commit 569280a300
1 changed files with 127 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

141
tokencost/model_prices.json
View File

@@ -10,9 +10,9 @@
"supports_function_calling": true
},
"gpt-4-turbo-preview": {
"max_tokens": 4096,
"max_input_tokens": 8192,
"max_output_tokens": 4096,
"max_tokens": 4096,
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00001,
"output_cost_per_token": 0.00003,
"litellm_provider": "openai",
@@ -75,7 +75,8 @@
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true
"supports_parallel_function_calling": true,
"supports_vision": true
},
"gpt-4-turbo-2024-04-09": {
"max_tokens": 4096,
@@ -86,7 +87,8 @@
"litellm_provider": "openai",
"mode": "chat",
"supports_function_calling": true,
"supports_parallel_function_calling": true
"supports_parallel_function_calling": true,
"supports_vision": true
},
"gpt-4-1106-preview": {
"max_tokens": 4096,
@@ -117,7 +119,8 @@
"input_cost_per_token": 0.00001,
"output_cost_per_token": 0.00003,
"litellm_provider": "openai",
"mode": "chat"
"mode": "chat",
"supports_vision": true
},
"gpt-4-1106-vision-preview": {
"max_tokens": 4096,
@@ -126,7 +129,8 @@
"input_cost_per_token": 0.00001,
"output_cost_per_token": 0.00003,
"litellm_provider": "openai",
"mode": "chat"
"mode": "chat",
"supports_vision": true
},
"gpt-3.5-turbo": {
"max_tokens": 4097,
@@ -209,6 +213,7 @@
"text-embedding-3-large": {
"max_tokens": 8191,
"max_input_tokens": 8191,
"output_vector_size": 3072,
"input_cost_per_token": 0.00000013,
"output_cost_per_token": 0.000000,
"litellm_provider": "openai",
@@ -217,6 +222,7 @@
"text-embedding-3-small": {
"max_tokens": 8191,
"max_input_tokens": 8191,
"output_vector_size": 1536,
"input_cost_per_token": 0.00000002,
"output_cost_per_token": 0.000000,
"litellm_provider": "openai",
@@ -225,6 +231,7 @@
"text-embedding-ada-002": {
"max_tokens": 8191,
"max_input_tokens": 8191,
"output_vector_size": 1536,
"input_cost_per_token": 0.0000001,
"output_cost_per_token": 0.000000,
"litellm_provider": "openai",
@@ -409,7 +416,8 @@
"input_cost_per_token": 0.00001,
"output_cost_per_token": 0.00003,
"litellm_provider": "azure",
"mode": "chat"
"mode": "chat",
"supports_vision": true
},
"azure/gpt-35-turbo-16k-0613": {
"max_tokens": 4096,
@@ -700,6 +708,16 @@
"mode": "chat",
"supports_function_calling": true
},
"mistral/open-mixtral-8x7b": {
"max_tokens": 8191,
"max_input_tokens": 32000,
"max_output_tokens": 8191,
"input_cost_per_token": 0.000002,
"output_cost_per_token": 0.000006,
"litellm_provider": "mistral",
"mode": "chat",
"supports_function_calling": true
},
"mistral/mistral-embed": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@@ -714,7 +732,28 @@
"input_cost_per_token": 0.00000070,
"output_cost_per_token": 0.00000080,
"litellm_provider": "groq",
"mode": "chat"
"mode": "chat",
"supports_function_calling": true
},
"groq/llama3-8b-8192": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000010,
"output_cost_per_token": 0.00000010,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/llama3-70b-8192": {
"max_tokens": 8192,
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"input_cost_per_token": 0.00000064,
"output_cost_per_token": 0.00000080,
"litellm_provider": "groq",
"mode": "chat",
"supports_function_calling": true
},
"groq/mixtral-8x7b-32768": {
"max_tokens": 32768,
@@ -723,7 +762,8 @@
"input_cost_per_token": 0.00000027,
"output_cost_per_token": 0.00000027,
"litellm_provider": "groq",
"mode": "chat"
"mode": "chat",
"supports_function_calling": true
},
"groq/gemma-7b-it": {
"max_tokens": 8192,
@@ -732,7 +772,8 @@
"input_cost_per_token": 0.00000010,
"output_cost_per_token": 0.00000010,
"litellm_provider": "groq",
"mode": "chat"
"mode": "chat",
"supports_function_calling": true
},
"claude-instant-1.2": {
"max_tokens": 8191,
@@ -1001,6 +1042,7 @@
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0215": {
@@ -1012,6 +1054,7 @@
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.5-pro-preview-0409": {
@@ -1023,6 +1066,7 @@
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": true,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-experimental": {
@@ -1034,6 +1078,7 @@
"litellm_provider": "vertex_ai-language-models",
"mode": "chat",
"supports_function_calling": false,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-pro-vision": {
@@ -1048,6 +1093,7 @@
"litellm_provider": "vertex_ai-vision-models",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-pro-vision": {
@@ -1062,6 +1108,7 @@
"litellm_provider": "vertex_ai-vision-models",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini-1.0-pro-vision-001": {
@@ -1076,10 +1123,12 @@
"litellm_provider": "vertex_ai-vision-models",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"vertex_ai/claude-3-sonnet@20240229": {
"max_tokens": 200000,
"max_tokens": 4096,
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000003,
"output_cost_per_token": 0.000015,
@@ -1087,13 +1136,23 @@
"mode": "chat"
},
"vertex_ai/claude-3-haiku@20240307": {
"max_tokens": 200000,
"max_tokens": 4096,
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.00000025,
"output_cost_per_token": 0.00000125,
"litellm_provider": "vertex_ai-anthropic_models",
"mode": "chat"
},
"vertex_ai/claude-3-opus@20240229": {
"max_tokens": 4096,
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.0000015,
"output_cost_per_token": 0.0000075,
"litellm_provider": "vertex_ai-anthropic_models",
"mode": "chat"
},
"textembedding-gecko": {
"max_tokens": 3072,
"max_input_tokens": 3072,
@@ -1144,6 +1203,27 @@
"mode": "embedding",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"text-embedding-preview-0409": {
"max_tokens": 3072,
"max_input_tokens": 3072,
"output_vector_size": 768,
"input_cost_per_token": 0.00000000625,
"input_cost_per_token_batch_requests": 0.000000005,
"output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding",
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"text-multilingual-embedding-preview-0409":{
"max_tokens": 3072,
"max_input_tokens": 3072,
"output_vector_size": 768,
"input_cost_per_token": 0.00000000625,
"output_cost_per_token": 0,
"litellm_provider": "vertex_ai-embedding-models",
"mode": "embedding",
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"palm/chat-bison": {
"max_tokens": 4096,
"max_input_tokens": 8192,
@@ -1224,8 +1304,23 @@
"litellm_provider": "gemini",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"supports_tool_choice": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"gemini/gemini-1.5-pro-latest": {
"max_tokens": 8192,
"max_input_tokens": 1048576,
"max_output_tokens": 8192,
"input_cost_per_token": 0,
"output_cost_per_token": 0,
"litellm_provider": "gemini",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"supports_tool_choice": true,
"source": "https://ai.google.dev/models/gemini"
},
"gemini/gemini-pro-vision": {
"max_tokens": 2048,
"max_input_tokens": 30720,
@@ -1235,6 +1330,7 @@
"litellm_provider": "gemini",
"mode": "chat",
"supports_function_calling": true,
"supports_vision": true,
"source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models"
},
"command-r": {
@@ -1439,6 +1535,13 @@
"litellm_provider": "openrouter",
"mode": "chat"
},
"openrouter/meta-llama/llama-3-70b-instruct": {
"max_tokens": 8192,
"input_cost_per_token": 0.0000008,
"output_cost_per_token": 0.0000008,
"litellm_provider": "openrouter",
"mode": "chat"
},
"j2-ultra": {
"max_tokens": 8192,
"max_input_tokens": 8192,
@@ -1697,6 +1800,15 @@
"litellm_provider": "bedrock",
"mode": "chat"
},
"anthropic.claude-3-opus-20240229-v1:0": {
"max_tokens": 4096,
"max_input_tokens": 200000,
"max_output_tokens": 4096,
"input_cost_per_token": 0.000015,
"output_cost_per_token": 0.000075,
"litellm_provider": "bedrock",
"mode": "chat"
},
"anthropic.claude-v1": {
"max_tokens": 8191,
"max_input_tokens": 100000,
@@ -2904,4 +3016,5 @@
"litellm_provider": "voyage",
"mode": "embedding"
}
}
}